Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3474 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7216. Min Range: -6.7216
Max Act: 6.7216. Min Act: -0.1700
Data Index: 5730932 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7216. Min Range: -6.7216
Max Act: 6.6591. Min Act: -0.1700
Data Index: 4618552 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7216. Min Range: -6.7216
Max Act: 6.6591. Min Act: -0.1700
Data Index: 4766719 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7216. Min Range: -6.7216
Max Act: 6.6591. Min Act: -0.1700
Data Index: 2886959 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7216. Min Range: -6.7216
Max Act: 6.5028. Min Act: -0.1700
Data Index: 5092946 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7216. Min Range: -6.7216
Max Act: 6.5341. Min Act: -0.1700
Data Index: 7903577 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7216. Min Range: -6.7216
Max Act: 6.5028. Min Act: -0.1700
Data Index: 6379367 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7216. Min Range: -6.7216
Max Act: 6.4403. Min Act: -0.1700
Data Index: 1215210 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7216. Min Range: -6.7216
Max Act: 6.4716. Min Act: -0.1700
Data Index: 671567 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7216. Min Range: -6.7216
Max Act: 6.4403. Min Act: -0.1700
Data Index: 7251206 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7216. Min Range: -6.7216
Max Act: 6.4403. Min Act: -0.1699
Data Index: 1027771 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7216. Min Range: -6.7216
Max Act: 6.4403. Min Act: -0.1700
Data Index: 4792297 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7216. Min Range: -6.7216
Max Act: 6.4091. Min Act: -0.1700
Data Index: 4925026 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7216. Min Range: -6.7216
Max Act: 6.4403. Min Act: -0.1700
Data Index: 444343 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7216. Min Range: -6.7216
Max Act: 6.4403. Min Act: -0.1700
Data Index: 7293388 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7216. Min Range: -6.7216
Max Act: 6.4403. Min Act: -0.1700
Data Index: 797653 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7216. Min Range: -6.7216
Max Act: 6.4403. Min Act: -0.1700
Data Index: 5129479 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7216. Min Range: -6.7216
Max Act: 6.4403. Min Act: -0.1699
Data Index: 6006422 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7216. Min Range: -6.7216
Max Act: 6.4716. Min Act: -0.1700
Data Index: 7221349 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7216. Min Range: -6.7216
Max Act: 6.4091. Min Act: -0.1700
Data Index: 6867407 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #19