Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3439 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3443. Min Range: -5.3443
Max Act: 5.3443. Min Act: -0.1700
Data Index: 6529428 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3443. Min Range: -5.3443
Max Act: 5.3443. Min Act: -0.1700
Data Index: 893807 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3443. Min Range: -5.3443
Max Act: 5.2506. Min Act: -0.1700
Data Index: 6529435 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3443. Min Range: -5.3443
Max Act: 5.2193. Min Act: -0.1700
Data Index: 91045 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3443. Min Range: -5.3443
Max Act: 5.1568. Min Act: -0.1700
Data Index: 5886497 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3443. Min Range: -5.3443
Max Act: 5.1568. Min Act: -0.1700
Data Index: 1449881 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3443. Min Range: -5.3443
Max Act: 5.1568. Min Act: -0.1700
Data Index: 6529436 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3443. Min Range: -5.3443
Max Act: 5.1256. Min Act: -0.1700
Data Index: 6270770 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3443. Min Range: -5.3443
Max Act: 5.1256. Min Act: -0.1700
Data Index: 7341401 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3443. Min Range: -5.3443
Max Act: 5.0943. Min Act: -0.1700
Data Index: 4442670 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3443. Min Range: -5.3443
Max Act: 5.0943. Min Act: -0.1700
Data Index: 5886500 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3443. Min Range: -5.3443
Max Act: 5.0631. Min Act: -0.1700
Data Index: 7789492 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3443. Min Range: -5.3443
Max Act: 5.0631. Min Act: -0.1700
Data Index: 2973213 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3443. Min Range: -5.3443
Max Act: 5.0318. Min Act: -0.1700
Data Index: 1509674 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3443. Min Range: -5.3443
Max Act: 5.0631. Min Act: -0.1700
Data Index: 3671032 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3443. Min Range: -5.3443
Max Act: 5.0318. Min Act: -0.1700
Data Index: 3194148 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3443. Min Range: -5.3443
Max Act: 5.0318. Min Act: -0.1700
Data Index: 6632880 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3443. Min Range: -5.3443
Max Act: 5.0318. Min Act: -0.1688
Data Index: 8110805 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3443. Min Range: -5.3443
Max Act: 5.0318. Min Act: -0.1700
Data Index: 3667779 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3443. Min Range: -5.3443
Max Act: 5.0318. Min Act: -0.1700
Data Index: 1016055 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19