Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3500 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7879. Min Range: -7.7879
Max Act: 7.7879. Min Act: -0.1700
Data Index: 4058578 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7879. Min Range: -7.7879
Max Act: 7.7879. Min Act: -0.1700
Data Index: 4955732 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7879. Min Range: -7.7879
Max Act: 7.7254. Min Act: -0.1700
Data Index: 3560362 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7879. Min Range: -7.7879
Max Act: 7.7254. Min Act: -0.1699
Data Index: 2647968 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7879. Min Range: -7.7879
Max Act: 7.6004. Min Act: -0.1700
Data Index: 5328166 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7879. Min Range: -7.7879
Max Act: 7.5379. Min Act: -0.1700
Data Index: 5660492 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7879. Min Range: -7.7879
Max Act: 7.4754. Min Act: -0.1700
Data Index: 126496 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7879. Min Range: -7.7879
Max Act: 7.4754. Min Act: -0.1700
Data Index: 4255756 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7879. Min Range: -7.7879
Max Act: 7.4754. Min Act: -0.1700
Data Index: 2971237 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7879. Min Range: -7.7879
Max Act: 7.4754. Min Act: -0.1700
Data Index: 5190063 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7879. Min Range: -7.7879
Max Act: 7.4754. Min Act: -0.1700
Data Index: 7981521 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7879. Min Range: -7.7879
Max Act: 7.4129. Min Act: -0.1700
Data Index: 5267911 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7879. Min Range: -7.7879
Max Act: 7.4129. Min Act: -0.1700
Data Index: 5418470 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7879. Min Range: -7.7879
Max Act: 7.4129. Min Act: -0.1700
Data Index: 802437 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7879. Min Range: -7.7879
Max Act: 7.4129. Min Act: -0.1700
Data Index: 5414583 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7879. Min Range: -7.7879
Max Act: 7.4129. Min Act: -0.1700
Data Index: 6321965 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7879. Min Range: -7.7879
Max Act: 7.4129. Min Act: -0.1700
Data Index: 3793178 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7879. Min Range: -7.7879
Max Act: 7.4129. Min Act: -0.1700
Data Index: 4861238 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7879. Min Range: -7.7879
Max Act: 7.4129. Min Act: -0.1700
Data Index: 5569509 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7879. Min Range: -7.7879
Max Act: 7.3504. Min Act: -0.1700
Data Index: 4241574 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19