Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3069 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1208. Min Range: -9.1208
Max Act: 9.1208. Min Act: -0.1700
Data Index: 3751873 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1208. Min Range: -9.1208
Max Act: 8.7458. Min Act: -0.1700
Data Index: 4291751 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1208. Min Range: -9.1208
Max Act: 8.6833. Min Act: -0.1700
Data Index: 5676233 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1208. Min Range: -9.1208
Max Act: 8.6208. Min Act: -0.1700
Data Index: 13656 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1208. Min Range: -9.1208
Max Act: 8.5583. Min Act: -0.1700
Data Index: 746685 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1208. Min Range: -9.1208
Max Act: 8.4958. Min Act: -0.1700
Data Index: 3118191 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1208. Min Range: -9.1208
Max Act: 8.4333. Min Act: -0.1700
Data Index: 2063711 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1208. Min Range: -9.1208
Max Act: 8.4333. Min Act: -0.1700
Data Index: 7384219 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1208. Min Range: -9.1208
Max Act: 8.3395. Min Act: -0.1700
Data Index: 323368 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1208. Min Range: -9.1208
Max Act: 8.1833. Min Act: -0.1700
Data Index: 7038317 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1208. Min Range: -9.1208
Max Act: 8.0583. Min Act: -0.1700
Data Index: 7582154 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1208. Min Range: -9.1208
Max Act: 7.9958. Min Act: -0.1700
Data Index: 5384659 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1208. Min Range: -9.1208
Max Act: 7.9020. Min Act: -0.1700
Data Index: 7102969 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1208. Min Range: -9.1208
Max Act: 7.8708. Min Act: -0.1700
Data Index: 3293154 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1208. Min Range: -9.1208
Max Act: 7.8708. Min Act: -0.1700
Data Index: 602888 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1208. Min Range: -9.1208
Max Act: 7.9020. Min Act: -0.1700
Data Index: 7371892 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1208. Min Range: -9.1208
Max Act: 7.8083. Min Act: -0.1700
Data Index: 5152997 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1208. Min Range: -9.1208
Max Act: 7.8395. Min Act: -0.1700
Data Index: 8009459 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1208. Min Range: -9.1208
Max Act: 7.7770. Min Act: -0.1700
Data Index: 977101 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1208. Min Range: -9.1208
Max Act: 7.8083. Min Act: -0.1700
Data Index: 5453110 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19