Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3877 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4341. Min Range: -6.4341
Max Act: 6.4341. Min Act: -0.1700
Data Index: 4309126 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4341. Min Range: -6.4341
Max Act: 6.3716. Min Act: -0.1700
Data Index: 2959394 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4341. Min Range: -6.4341
Max Act: 6.1216. Min Act: -0.1700
Data Index: 2979858 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4341. Min Range: -6.4341
Max Act: 6.0904. Min Act: -0.1700
Data Index: 2324531 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4341. Min Range: -6.4341
Max Act: 6.0279. Min Act: -0.1700
Data Index: 2606811 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4341. Min Range: -6.4341
Max Act: 6.0279. Min Act: -0.1700
Data Index: 5341051 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4341. Min Range: -6.4341
Max Act: 5.9966. Min Act: -0.1700
Data Index: 2271917 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4341. Min Range: -6.4341
Max Act: 5.9029. Min Act: -0.1700
Data Index: 923902 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4341. Min Range: -6.4341
Max Act: 5.9341. Min Act: -0.1700
Data Index: 1626721 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4341. Min Range: -6.4341
Max Act: 5.9029. Min Act: -0.1700
Data Index: 6796585 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4341. Min Range: -6.4341
Max Act: 5.8716. Min Act: -0.1700
Data Index: 4304834 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4341. Min Range: -6.4341
Max Act: 5.8404. Min Act: -0.1700
Data Index: 2272840 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4341. Min Range: -6.4341
Max Act: 5.8716. Min Act: -0.1700
Data Index: 565870 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4341. Min Range: -6.4341
Max Act: 5.8091. Min Act: -0.1700
Data Index: 1630486 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4341. Min Range: -6.4341
Max Act: 5.7779. Min Act: -0.1700
Data Index: 8236597 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4341. Min Range: -6.4341
Max Act: 5.7779. Min Act: -0.1700
Data Index: 3693178 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4341. Min Range: -6.4341
Max Act: 5.7779. Min Act: -0.1700
Data Index: 2291553 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4341. Min Range: -6.4341
Max Act: 5.7466. Min Act: -0.1700
Data Index: 6707672 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4341. Min Range: -6.4341
Max Act: 5.7466. Min Act: -0.1700
Data Index: 930709 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4341. Min Range: -6.4341
Max Act: 5.7154. Min Act: -0.1700
Data Index: 3577210 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #19