Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 66 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5995. Min Range: -6.5995
Max Act: 6.5995. Min Act: -0.1700
Data Index: 3213406 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5995. Min Range: -6.5995
Max Act: 6.5682. Min Act: -0.1700
Data Index: 4336982 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5995. Min Range: -6.5995
Max Act: 6.5370. Min Act: -0.1700
Data Index: 1096476 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5995. Min Range: -6.5995
Max Act: 6.5057. Min Act: -0.1700
Data Index: 4641206 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5995. Min Range: -6.5995
Max Act: 6.5057. Min Act: -0.1700
Data Index: 5213406 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5995. Min Range: -6.5995
Max Act: 6.4745. Min Act: -0.1700
Data Index: 5222962 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5995. Min Range: -6.5995
Max Act: 6.3495. Min Act: -0.1700
Data Index: 87684 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5995. Min Range: -6.5995
Max Act: 6.3495. Min Act: -0.1700
Data Index: 1107848 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5995. Min Range: -6.5995
Max Act: 6.3495. Min Act: -0.1700
Data Index: 8133363 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5995. Min Range: -6.5995
Max Act: 6.3182. Min Act: -0.1700
Data Index: 45300 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5995. Min Range: -6.5995
Max Act: 6.3182. Min Act: -0.1700
Data Index: 2384550 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5995. Min Range: -6.5995
Max Act: 6.2870. Min Act: -0.1700
Data Index: 8615513 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5995. Min Range: -6.5995
Max Act: 6.3182. Min Act: -0.1700
Data Index: 2196715 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5995. Min Range: -6.5995
Max Act: 6.2870. Min Act: -0.1700
Data Index: 458687 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5995. Min Range: -6.5995
Max Act: 6.2870. Min Act: -0.1700
Data Index: 6124025 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5995. Min Range: -6.5995
Max Act: 6.2870. Min Act: -0.1700
Data Index: 751829 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5995. Min Range: -6.5995
Max Act: 6.2557. Min Act: -0.1700
Data Index: 4821405 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5995. Min Range: -6.5995
Max Act: 6.2557. Min Act: -0.1700
Data Index: 5574569 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5995. Min Range: -6.5995
Max Act: 6.2557. Min Act: -0.1700
Data Index: 127964 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5995. Min Range: -6.5995
Max Act: 6.2557. Min Act: -0.1700
Data Index: 7132388 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #19