Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1028 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.0825. Min Range: -12.0825
Max Act: 12.0825. Min Act: -0.1700
Data Index: 2657836 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.0825. Min Range: -12.0825
Max Act: 11.9575. Min Act: -0.1700
Data Index: 8429805 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.0825. Min Range: -12.0825
Max Act: 11.8950. Min Act: -0.1700
Data Index: 2490406 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.0825. Min Range: -12.0825
Max Act: 11.8950. Min Act: -0.1700
Data Index: 4623188 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.0825. Min Range: -12.0825
Max Act: 11.8950. Min Act: -0.1700
Data Index: 3363293 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.0825. Min Range: -12.0825
Max Act: 11.8325. Min Act: -0.1700
Data Index: 2743755 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.0825. Min Range: -12.0825
Max Act: 11.7075. Min Act: -0.1700
Data Index: 8443628 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.0825. Min Range: -12.0825
Max Act: 11.7700. Min Act: -0.1700
Data Index: 3972256 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.0825. Min Range: -12.0825
Max Act: 11.7075. Min Act: -0.1700
Data Index: 8322436 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.0825. Min Range: -12.0825
Max Act: 11.7075. Min Act: -0.1700
Data Index: 5948648 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.0825. Min Range: -12.0825
Max Act: 11.6450. Min Act: -0.1700
Data Index: 3491230 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.0825. Min Range: -12.0825
Max Act: 11.5825. Min Act: -0.1700
Data Index: 6775434 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.0825. Min Range: -12.0825
Max Act: 11.5825. Min Act: -0.1700
Data Index: 512463 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.0825. Min Range: -12.0825
Max Act: 11.5825. Min Act: -0.1700
Data Index: 7389498 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.0825. Min Range: -12.0825
Max Act: 11.5825. Min Act: -0.1700
Data Index: 6442401 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.0825. Min Range: -12.0825
Max Act: 11.5200. Min Act: -0.1700
Data Index: 5650548 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.0825. Min Range: -12.0825
Max Act: 11.5200. Min Act: -0.1700
Data Index: 5167966 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.0825. Min Range: -12.0825
Max Act: 11.5200. Min Act: -0.1700
Data Index: 7258060 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.0825. Min Range: -12.0825
Max Act: 11.5200. Min Act: -0.1700
Data Index: 8571319 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.0825. Min Range: -12.0825
Max Act: 11.4575. Min Act: -0.1700
Data Index: 1292969 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19