Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4388 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9584. Min Range: -3.9584
Max Act: 3.9584. Min Act: -0.1700
Data Index: 2368303 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9584. Min Range: -3.9584
Max Act: 3.8177. Min Act: -0.1700
Data Index: 3209372 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9584. Min Range: -3.9584
Max Act: 3.7708. Min Act: -0.1700
Data Index: 7074578 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9584. Min Range: -3.9584
Max Act: 3.7082. Min Act: -0.1700
Data Index: 746589 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9584. Min Range: -3.9584
Max Act: 3.7395. Min Act: -0.1700
Data Index: 3584120 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9584. Min Range: -3.9584
Max Act: 3.6613. Min Act: -0.1700
Data Index: 4232497 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9584. Min Range: -3.9584
Max Act: 3.6456. Min Act: -0.1700
Data Index: 4453290 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9584. Min Range: -3.9584
Max Act: 3.6300. Min Act: -0.1700
Data Index: 5743678 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9584. Min Range: -3.9584
Max Act: 3.6456. Min Act: -0.1700
Data Index: 3393190 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9584. Min Range: -3.9584
Max Act: 3.6143. Min Act: -0.1700
Data Index: 8756537 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9584. Min Range: -3.9584
Max Act: 3.6143. Min Act: -0.1700
Data Index: 1210654 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9584. Min Range: -3.9584
Max Act: 3.6143. Min Act: -0.1700
Data Index: 1842262 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9584. Min Range: -3.9584
Max Act: 3.5987. Min Act: -0.1700
Data Index: 8414328 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9584. Min Range: -3.9584
Max Act: 3.5517. Min Act: -0.1700
Data Index: 8136049 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9584. Min Range: -3.9584
Max Act: 3.5517. Min Act: -0.1700
Data Index: 4157475 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9584. Min Range: -3.9584
Max Act: 3.5360. Min Act: -0.1700
Data Index: 6442502 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9584. Min Range: -3.9584
Max Act: 3.5360. Min Act: -0.1700
Data Index: 5950524 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9584. Min Range: -3.9584
Max Act: 3.5517. Min Act: -0.1700
Data Index: 6984043 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9584. Min Range: -3.9584
Max Act: 3.5204. Min Act: -0.1700
Data Index: 915181 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9584. Min Range: -3.9584
Max Act: 3.5360. Min Act: -0.1700
Data Index: 210058 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19