Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2595 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.2982. Min Act: -0.1700
Data Index: 112632 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.2670. Min Act: -0.1700
Data Index: 112634 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.1732. Min Act: -0.1700
Data Index: 825304 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.0795. Min Act: -0.1700
Data Index: 8417726 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.0482. Min Act: -0.1700
Data Index: 1414721 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.0482. Min Act: -0.1700
Data Index: 825305 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2982. Min Range: -4.2982
Max Act: 4.0169. Min Act: -0.1700
Data Index: 5877300 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2982. Min Range: -4.2982
Max Act: 3.9857. Min Act: -0.1700
Data Index: 2542063 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2982. Min Range: -4.2982
Max Act: 3.9544. Min Act: -0.1700
Data Index: 1293898 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2982. Min Range: -4.2982
Max Act: 3.9544. Min Act: -0.1700
Data Index: 565192 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2982. Min Range: -4.2982
Max Act: 3.9544. Min Act: -0.1700
Data Index: 1330769 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2982. Min Range: -4.2982
Max Act: 3.9388. Min Act: -0.1700
Data Index: 6070012 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2982. Min Range: -4.2982
Max Act: 3.9231. Min Act: -0.1700
Data Index: 306502 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2982. Min Range: -4.2982
Max Act: 3.9075. Min Act: -0.1700
Data Index: 8447025 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2982. Min Range: -4.2982
Max Act: 3.8919. Min Act: -0.1700
Data Index: 8294662 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2982. Min Range: -4.2982
Max Act: 3.9075. Min Act: -0.1700
Data Index: 6127854 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2982. Min Range: -4.2982
Max Act: 3.8919. Min Act: -0.1700
Data Index: 825303 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2982. Min Range: -4.2982
Max Act: 3.9231. Min Act: -0.1700
Data Index: 6442775 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2982. Min Range: -4.2982
Max Act: 3.8919. Min Act: -0.1700
Data Index: 6507753 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2982. Min Range: -4.2982
Max Act: 3.8763. Min Act: -0.1700
Data Index: 3065333 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19