Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4007 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.9086. Min Act: -0.1699
Data Index: 3733173 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.9086. Min Act: -0.1700
Data Index: 5349219 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.9086. Min Act: -0.1700
Data Index: 8173496 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.8461. Min Act: -0.1700
Data Index: 924713 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.8461. Min Act: -0.1700
Data Index: 2995131 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.8461. Min Act: -0.1699
Data Index: 577732 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.8461. Min Act: -0.1700
Data Index: 2386329 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.8461. Min Act: -0.1700
Data Index: 2293945 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.8461. Min Act: -0.1700
Data Index: 3632883 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.8461. Min Act: -0.1700
Data Index: 8148656 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.8461. Min Act: -0.1700
Data Index: 7435484 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.8773. Min Act: -0.1700
Data Index: 7339203 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.8461. Min Act: -0.1700
Data Index: 5733393 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.8461. Min Act: -0.1700
Data Index: 4683884 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.8148. Min Act: -0.1700
Data Index: 2203028 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.8148. Min Act: -0.1700
Data Index: 541439 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.8148. Min Act: -0.1700
Data Index: 1120318 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.8148. Min Act: -0.1700
Data Index: 3085782 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.8148. Min Act: -0.1700
Data Index: 1279594 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9086. Min Range: -3.9086
Max Act: 3.8461. Min Act: -0.1700
Data Index: 625505 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19