Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3901 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1253. Min Range: -8.1253
Max Act: 8.1253. Min Act: -0.1700
Data Index: 4784279 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1253. Min Range: -8.1253
Max Act: 8.0628. Min Act: -0.1700
Data Index: 7865478 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1253. Min Range: -8.1253
Max Act: 8.0628. Min Act: -0.1700
Data Index: 6647901 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1253. Min Range: -8.1253
Max Act: 8.0003. Min Act: -0.1700
Data Index: 744288 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1253. Min Range: -8.1253
Max Act: 8.0003. Min Act: -0.1700
Data Index: 1537059 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1253. Min Range: -8.1253
Max Act: 8.0003. Min Act: -0.1700
Data Index: 6472138 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1253. Min Range: -8.1253
Max Act: 7.9378. Min Act: -0.1700
Data Index: 799083 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1253. Min Range: -8.1253
Max Act: 7.9378. Min Act: -0.1700
Data Index: 2536431 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1253. Min Range: -8.1253
Max Act: 7.9378. Min Act: -0.1700
Data Index: 362624 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1253. Min Range: -8.1253
Max Act: 7.8753. Min Act: -0.1700
Data Index: 4291696 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1253. Min Range: -8.1253
Max Act: 7.8753. Min Act: -0.1700
Data Index: 5322328 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1253. Min Range: -8.1253
Max Act: 7.8128. Min Act: -0.1700
Data Index: 2381184 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1253. Min Range: -8.1253
Max Act: 7.8128. Min Act: -0.1700
Data Index: 3012839 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1253. Min Range: -8.1253
Max Act: 7.8128. Min Act: -0.1700
Data Index: 7916518 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1253. Min Range: -8.1253
Max Act: 7.8128. Min Act: -0.1700
Data Index: 1115179 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1253. Min Range: -8.1253
Max Act: 7.7503. Min Act: -0.1700
Data Index: 7294373 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1253. Min Range: -8.1253
Max Act: 7.7503. Min Act: -0.1700
Data Index: 3229222 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1253. Min Range: -8.1253
Max Act: 7.7503. Min Act: -0.1700
Data Index: 5384958 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1253. Min Range: -8.1253
Max Act: 7.7503. Min Act: -0.1700
Data Index: 7800573 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1253. Min Range: -8.1253
Max Act: 7.7191. Min Act: -0.1700
Data Index: 6530650 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19