Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3067 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.1358. Min Range: -2.1358
Max Act: 2.1358. Min Act: -0.1700
Data Index: 3818952 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1358. Min Range: -2.1358
Max Act: 2.1191. Min Act: -0.1700
Data Index: 4823119 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1358. Min Range: -2.1358
Max Act: 2.0856. Min Act: -0.1700
Data Index: 5887496 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1358. Min Range: -2.1358
Max Act: 2.0856. Min Act: -0.1700
Data Index: 2152995 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1358. Min Range: -2.1358
Max Act: 2.0688. Min Act: -0.1700
Data Index: 3248133 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1358. Min Range: -2.1358
Max Act: 2.0520. Min Act: -0.1700
Data Index: 3818951 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1358. Min Range: -2.1358
Max Act: 2.0352. Min Act: -0.1700
Data Index: 3818954 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1358. Min Range: -2.1358
Max Act: 2.0688. Min Act: -0.1700
Data Index: 5628292 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1358. Min Range: -2.1358
Max Act: 2.0520. Min Act: -0.1700
Data Index: 3818950 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1358. Min Range: -2.1358
Max Act: 2.0352. Min Act: -0.1700
Data Index: 1636804 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1358. Min Range: -2.1358
Max Act: 2.0352. Min Act: -0.1700
Data Index: 8408261 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1358. Min Range: -2.1358
Max Act: 2.0183. Min Act: -0.1700
Data Index: 3492989 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1358. Min Range: -2.1358
Max Act: 2.0183. Min Act: -0.1700
Data Index: 7128732 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1358. Min Range: -2.1358
Max Act: 2.0183. Min Act: -0.1700
Data Index: 5411534 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1358. Min Range: -2.1358
Max Act: 2.0352. Min Act: -0.1700
Data Index: 1839953 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1358. Min Range: -2.1358
Max Act: 2.0183. Min Act: -0.1700
Data Index: 3818955 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1358. Min Range: -2.1358
Max Act: 2.0183. Min Act: -0.1700
Data Index: 6055034 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1358. Min Range: -2.1358
Max Act: 2.0183. Min Act: -0.1700
Data Index: 565603 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1358. Min Range: -2.1358
Max Act: 2.0352. Min Act: -0.1700
Data Index: 4123010 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1358. Min Range: -2.1358
Max Act: 2.0183. Min Act: -0.1700
Data Index: 2770384 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19