Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4689 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.5662. Min Act: -0.1700
Data Index: 6831806 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.4724. Min Act: -0.1700
Data Index: 3686279 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.4099. Min Act: -0.1700
Data Index: 6819172 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.3787. Min Act: -0.1700
Data Index: 4362947 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.3474. Min Act: -0.1700
Data Index: 8434854 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.3474. Min Act: -0.1700
Data Index: 3829560 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.3162. Min Act: -0.1700
Data Index: 7237962 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.2849. Min Act: -0.1700
Data Index: 6826007 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.2849. Min Act: -0.1700
Data Index: 1531537 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.2849. Min Act: -0.1700
Data Index: 184084 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.2849. Min Act: -0.1700
Data Index: 5871554 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.2537. Min Act: -0.1700
Data Index: 3652146 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.2537. Min Act: -0.1700
Data Index: 2092314 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.2849. Min Act: -0.1700
Data Index: 3181102 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.2537. Min Act: -0.1699
Data Index: 5482766 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.2537. Min Act: -0.1700
Data Index: 2021938 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.2224. Min Act: -0.1700
Data Index: 3556086 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.2224. Min Act: -0.1700
Data Index: 4321188 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.2224. Min Act: -0.1700
Data Index: 906117 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.2224. Min Act: -0.1700
Data Index: 5603603 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #19