Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 683 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6547. Min Range: -5.6547
Max Act: 5.6547. Min Act: -0.1700
Data Index: 6084283 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6547. Min Range: -5.6547
Max Act: 5.4047. Min Act: -0.1700
Data Index: 6309045 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6547. Min Range: -5.6547
Max Act: 5.2485. Min Act: -0.1700
Data Index: 8639328 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6547. Min Range: -5.6547
Max Act: 5.2485. Min Act: -0.1700
Data Index: 6929061 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6547. Min Range: -5.6547
Max Act: 5.2172. Min Act: -0.1700
Data Index: 5760897 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6547. Min Range: -5.6547
Max Act: 5.2172. Min Act: -0.1700
Data Index: 4520171 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6547. Min Range: -5.6547
Max Act: 5.1860. Min Act: -0.1700
Data Index: 5590766 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6547. Min Range: -5.6547
Max Act: 5.1547. Min Act: -0.1700
Data Index: 1309836 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6547. Min Range: -5.6547
Max Act: 5.1547. Min Act: -0.1700
Data Index: 16921 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6547. Min Range: -5.6547
Max Act: 5.1547. Min Act: -0.1700
Data Index: 1973510 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6547. Min Range: -5.6547
Max Act: 5.0922. Min Act: -0.1700
Data Index: 8242567 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6547. Min Range: -5.6547
Max Act: 5.0922. Min Act: -0.1700
Data Index: 7214110 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6547. Min Range: -5.6547
Max Act: 5.0922. Min Act: -0.1700
Data Index: 2407752 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6547. Min Range: -5.6547
Max Act: 5.0922. Min Act: -0.1700
Data Index: 1259291 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6547. Min Range: -5.6547
Max Act: 5.0922. Min Act: -0.1700
Data Index: 8668860 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6547. Min Range: -5.6547
Max Act: 5.0610. Min Act: -0.1700
Data Index: 980226 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6547. Min Range: -5.6547
Max Act: 5.0610. Min Act: -0.1700
Data Index: 1411344 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6547. Min Range: -5.6547
Max Act: 5.0610. Min Act: -0.1700
Data Index: 429695 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6547. Min Range: -5.6547
Max Act: 5.0610. Min Act: -0.1700
Data Index: 1868643 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6547. Min Range: -5.6547
Max Act: 5.0610. Min Act: -0.1700
Data Index: 7488996 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19