Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3173 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1858. Min Range: -7.1858
Max Act: 7.1858. Min Act: -0.1700
Data Index: 3221825 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1858. Min Range: -7.1858
Max Act: 7.1545. Min Act: -0.1700
Data Index: 2578817 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1858. Min Range: -7.1858
Max Act: 6.9670. Min Act: -0.1700
Data Index: 3054873 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1858. Min Range: -7.1858
Max Act: 6.8420. Min Act: -0.1700
Data Index: 7821670 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1858. Min Range: -7.1858
Max Act: 6.8108. Min Act: -0.1700
Data Index: 1110626 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1858. Min Range: -7.1858
Max Act: 6.7795. Min Act: -0.1700
Data Index: 2578828 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1858. Min Range: -7.1858
Max Act: 6.7795. Min Act: -0.1700
Data Index: 3931386 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1858. Min Range: -7.1858
Max Act: 6.7795. Min Act: -0.1700
Data Index: 2671481 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1858. Min Range: -7.1858
Max Act: 6.7483. Min Act: -0.1700
Data Index: 1861599 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1858. Min Range: -7.1858
Max Act: 6.7483. Min Act: -0.1700
Data Index: 6571238 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1858. Min Range: -7.1858
Max Act: 6.7170. Min Act: -0.1700
Data Index: 3682873 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1858. Min Range: -7.1858
Max Act: 6.6858. Min Act: -0.1700
Data Index: 1606150 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1858. Min Range: -7.1858
Max Act: 6.6233. Min Act: -0.1700
Data Index: 2564495 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1858. Min Range: -7.1858
Max Act: 6.6545. Min Act: -0.1700
Data Index: 6910727 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1858. Min Range: -7.1858
Max Act: 6.6858. Min Act: -0.1700
Data Index: 4527918 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1858. Min Range: -7.1858
Max Act: 6.6233. Min Act: -0.1700
Data Index: 3038024 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1858. Min Range: -7.1858
Max Act: 6.6233. Min Act: -0.1700
Data Index: 4863153 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1858. Min Range: -7.1858
Max Act: 6.6545. Min Act: -0.1700
Data Index: 3370374 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1858. Min Range: -7.1858
Max Act: 6.6233. Min Act: -0.1700
Data Index: 2298922 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1858. Min Range: -7.1858
Max Act: 6.6233. Min Act: -0.1700
Data Index: 4631304 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19