Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4153 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.4321. Min Act: -0.1700
Data Index: 7512940 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.4009. Min Act: -0.1700
Data Index: 7709300 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.3696. Min Act: -0.1700
Data Index: 4733087 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.3384. Min Act: -0.1700
Data Index: 1757923 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.3071. Min Act: -0.1700
Data Index: 7964940 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.3071. Min Act: -0.1700
Data Index: 8292306 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.2134. Min Act: -0.1700
Data Index: 1539159 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.2134. Min Act: -0.1700
Data Index: 1968503 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.2134. Min Act: -0.1700
Data Index: 993851 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.1509. Min Act: -0.1699
Data Index: 1473578 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.1196. Min Act: -0.1700
Data Index: 7266286 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.1196. Min Act: -0.1700
Data Index: 3388024 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.1196. Min Act: -0.1700
Data Index: 5317251 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.1196. Min Act: -0.1700
Data Index: 4492511 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.0884. Min Act: -0.1700
Data Index: 1890884 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.0884. Min Act: -0.1700
Data Index: 4244557 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.0571. Min Act: -0.1700
Data Index: 1103316 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.0571. Min Act: -0.1700
Data Index: 1896825 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.0571. Min Act: -0.1700
Data Index: 8205640 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4321. Min Range: -6.4321
Max Act: 6.0571. Min Act: -0.1700
Data Index: 7733473 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19