Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 24 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2343. Min Range: -3.2343
Max Act: 3.2343. Min Act: -0.1700
Data Index: 763018 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2343. Min Range: -3.2343
Max Act: 3.2186. Min Act: -0.1700
Data Index: 2453671 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2343. Min Range: -3.2343
Max Act: 3.2029. Min Act: -0.1700
Data Index: 3910684 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2343. Min Range: -3.2343
Max Act: 3.1871. Min Act: -0.1700
Data Index: 8032194 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2343. Min Range: -3.2343
Max Act: 3.1871. Min Act: -0.1700
Data Index: 3331139 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2343. Min Range: -3.2343
Max Act: 3.1557. Min Act: -0.1700
Data Index: 7888363 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2343. Min Range: -3.2343
Max Act: 3.1557. Min Act: -0.1700
Data Index: 288508 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2343. Min Range: -3.2343
Max Act: 3.1714. Min Act: -0.1700
Data Index: 1048162 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2343. Min Range: -3.2343
Max Act: 3.1399. Min Act: -0.1700
Data Index: 6726039 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2343. Min Range: -3.2343
Max Act: 3.1557. Min Act: -0.1700
Data Index: 1313996 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2343. Min Range: -3.2343
Max Act: 3.1399. Min Act: -0.1700
Data Index: 6157044 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2343. Min Range: -3.2343
Max Act: 3.1399. Min Act: -0.1700
Data Index: 6305993 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2343. Min Range: -3.2343
Max Act: 3.1399. Min Act: -0.1700
Data Index: 5586536 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2343. Min Range: -3.2343
Max Act: 3.1242. Min Act: -0.1700
Data Index: 4612773 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2343. Min Range: -3.2343
Max Act: 3.1084. Min Act: -0.1700
Data Index: 4666552 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2343. Min Range: -3.2343
Max Act: 3.0927. Min Act: -0.1700
Data Index: 960471 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2343. Min Range: -3.2343
Max Act: 3.0927. Min Act: -0.1700
Data Index: 7909947 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2343. Min Range: -3.2343
Max Act: 3.0769. Min Act: -0.1700
Data Index: 5437754 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2343. Min Range: -3.2343
Max Act: 3.0769. Min Act: -0.1700
Data Index: 149182 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2343. Min Range: -3.2343
Max Act: 3.0769. Min Act: -0.1700
Data Index: 2856050 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19