Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3631 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3153. Min Range: -7.3153
Max Act: 7.3153. Min Act: -0.1700
Data Index: 8340537 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3153. Min Range: -7.3153
Max Act: 7.1278. Min Act: -0.1700
Data Index: 8436148 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3153. Min Range: -7.3153
Max Act: 7.0653. Min Act: -0.1700
Data Index: 5787851 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3153. Min Range: -7.3153
Max Act: 6.9716. Min Act: -0.1700
Data Index: 5523021 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3153. Min Range: -7.3153
Max Act: 6.9403. Min Act: -0.1700
Data Index: 3138282 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3153. Min Range: -7.3153
Max Act: 6.9091. Min Act: -0.1700
Data Index: 6623471 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3153. Min Range: -7.3153
Max Act: 6.8778. Min Act: -0.1700
Data Index: 8045234 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3153. Min Range: -7.3153
Max Act: 6.8778. Min Act: -0.1700
Data Index: 2354609 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3153. Min Range: -7.3153
Max Act: 6.8778. Min Act: -0.1700
Data Index: 1886367 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3153. Min Range: -7.3153
Max Act: 6.7216. Min Act: -0.1700
Data Index: 2578895 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3153. Min Range: -7.3153
Max Act: 6.7216. Min Act: -0.1700
Data Index: 8010575 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3153. Min Range: -7.3153
Max Act: 6.7216. Min Act: -0.1699
Data Index: 4354503 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3153. Min Range: -7.3153
Max Act: 6.7216. Min Act: -0.1700
Data Index: 3097669 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3153. Min Range: -7.3153
Max Act: 6.7216. Min Act: -0.1700
Data Index: 5188731 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3153. Min Range: -7.3153
Max Act: 6.7216. Min Act: -0.1700
Data Index: 5297085 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3153. Min Range: -7.3153
Max Act: 6.7216. Min Act: -0.1700
Data Index: 4558154 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3153. Min Range: -7.3153
Max Act: 6.6903. Min Act: -0.1700
Data Index: 7280826 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3153. Min Range: -7.3153
Max Act: 6.6903. Min Act: -0.1700
Data Index: 6749659 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3153. Min Range: -7.3153
Max Act: 6.6591. Min Act: -0.1700
Data Index: 7770810 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3153. Min Range: -7.3153
Max Act: 6.6903. Min Act: -0.1700
Data Index: 7342838 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19