Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6369 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4334. Min Range: -2.4334
Max Act: 2.4334. Min Act: -0.1700
Data Index: 2564532 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4334. Min Range: -2.4334
Max Act: 2.4171. Min Act: -0.1700
Data Index: 771044 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4334. Min Range: -2.4334
Max Act: 2.3681. Min Act: -0.1700
Data Index: 668729 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4334. Min Range: -2.4334
Max Act: 2.3518. Min Act: -0.1700
Data Index: 4853253 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4334. Min Range: -2.4334
Max Act: 2.3190. Min Act: -0.1700
Data Index: 7841691 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4334. Min Range: -2.4334
Max Act: 2.3354. Min Act: -0.1700
Data Index: 5663908 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4334. Min Range: -2.4334
Max Act: 2.3190. Min Act: -0.1700
Data Index: 5861419 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4334. Min Range: -2.4334
Max Act: 2.3025. Min Act: -0.1700
Data Index: 1776509 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4334. Min Range: -2.4334
Max Act: 2.2696. Min Act: -0.1700
Data Index: 5428476 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4334. Min Range: -2.4334
Max Act: 2.2696. Min Act: -0.1700
Data Index: 4187846 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4334. Min Range: -2.4334
Max Act: 2.2531. Min Act: -0.1700
Data Index: 835026 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4334. Min Range: -2.4334
Max Act: 2.2696. Min Act: -0.1692
Data Index: 5045492 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4334. Min Range: -2.4334
Max Act: 2.2365. Min Act: -0.1700
Data Index: 1867459 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4334. Min Range: -2.4334
Max Act: 2.2200. Min Act: -0.1700
Data Index: 4225984 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4334. Min Range: -2.4334
Max Act: 2.2200. Min Act: -0.1700
Data Index: 3109838 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4334. Min Range: -2.4334
Max Act: 2.2200. Min Act: -0.1690
Data Index: 3197834 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4334. Min Range: -2.4334
Max Act: 2.2200. Min Act: -0.1700
Data Index: 24434 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4334. Min Range: -2.4334
Max Act: 2.2034. Min Act: -0.1700
Data Index: 848960 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4334. Min Range: -2.4334
Max Act: 2.2034. Min Act: -0.1700
Data Index: 5035237 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4334. Min Range: -2.4334
Max Act: 2.2034. Min Act: -0.1700
Data Index: 3820038 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19