Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3625 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8442. Min Range: -6.8442
Max Act: 6.8442. Min Act: -0.1700
Data Index: 7387707 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8442. Min Range: -6.8442
Max Act: 6.7192. Min Act: -0.1700
Data Index: 2612126 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8442. Min Range: -6.8442
Max Act: 6.3442. Min Act: -0.1700
Data Index: 360768 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8442. Min Range: -6.8442
Max Act: 6.3130. Min Act: -0.1700
Data Index: 310738 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8442. Min Range: -6.8442
Max Act: 6.2817. Min Act: -0.1700
Data Index: 7839086 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8442. Min Range: -6.8442
Max Act: 6.2817. Min Act: -0.1700
Data Index: 226131 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8442. Min Range: -6.8442
Max Act: 6.2817. Min Act: -0.1700
Data Index: 5979875 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8442. Min Range: -6.8442
Max Act: 6.2817. Min Act: -0.1700
Data Index: 2334009 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8442. Min Range: -6.8442
Max Act: 6.2817. Min Act: -0.1700
Data Index: 3679522 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8442. Min Range: -6.8442
Max Act: 6.2817. Min Act: -0.1700
Data Index: 3581802 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8442. Min Range: -6.8442
Max Act: 6.2505. Min Act: -0.1700
Data Index: 2040104 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8442. Min Range: -6.8442
Max Act: 6.2505. Min Act: -0.1700
Data Index: 6546933 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8442. Min Range: -6.8442
Max Act: 6.2192. Min Act: -0.1700
Data Index: 4500460 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8442. Min Range: -6.8442
Max Act: 6.2192. Min Act: -0.1700
Data Index: 2458164 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8442. Min Range: -6.8442
Max Act: 6.1880. Min Act: -0.1700
Data Index: 7994413 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8442. Min Range: -6.8442
Max Act: 6.1567. Min Act: -0.1700
Data Index: 980767 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8442. Min Range: -6.8442
Max Act: 6.1255. Min Act: -0.1700
Data Index: 802774 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8442. Min Range: -6.8442
Max Act: 6.0942. Min Act: -0.1700
Data Index: 5279909 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8442. Min Range: -6.8442
Max Act: 6.1255. Min Act: -0.1700
Data Index: 7504828 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8442. Min Range: -6.8442
Max Act: 6.1255. Min Act: -0.1700
Data Index: 5413626 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19