Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1189 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.9956. Min Act: -0.1700
Data Index: 3630885 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.9018. Min Act: -0.1700
Data Index: 1820269 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.7456. Min Act: -0.1700
Data Index: 5209686 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.6831. Min Act: -0.1700
Data Index: 4908780 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.6831. Min Act: -0.1700
Data Index: 3837961 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.6518. Min Act: -0.1700
Data Index: 7573593 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.6831. Min Act: -0.1700
Data Index: 659870 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.6206. Min Act: -0.1700
Data Index: 697869 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.6206. Min Act: -0.1700
Data Index: 1063414 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.5893. Min Act: -0.1700
Data Index: 7970009 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.5893. Min Act: -0.1700
Data Index: 5265501 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.5268. Min Act: -0.1700
Data Index: 5150272 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.5268. Min Act: -0.1700
Data Index: 4648732 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.4956. Min Act: -0.1700
Data Index: 3488013 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.4643. Min Act: -0.1700
Data Index: 2896045 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.4331. Min Act: -0.1700
Data Index: 357149 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.4331. Min Act: -0.1700
Data Index: 6769350 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.4331. Min Act: -0.1700
Data Index: 1443723 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.4331. Min Act: -0.1700
Data Index: 8519985 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9956. Min Range: -6.9956
Max Act: 6.4018. Min Act: -0.1700
Data Index: 2129347 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #19