Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6099 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3083. Min Range: -7.3083
Max Act: 7.2770. Min Act: -0.1700
Data Index: 2924926 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3083. Min Range: -7.3083
Max Act: 7.3083. Min Act: -0.1700
Data Index: 7162650 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3083. Min Range: -7.3083
Max Act: 7.1208. Min Act: -0.1700
Data Index: 7379218 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3083. Min Range: -7.3083
Max Act: 7.0270. Min Act: -0.1700
Data Index: 7786052 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3083. Min Range: -7.3083
Max Act: 6.9645. Min Act: -0.1700
Data Index: 1738959 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3083. Min Range: -7.3083
Max Act: 6.8708. Min Act: -0.1700
Data Index: 5214498 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3083. Min Range: -7.3083
Max Act: 6.8708. Min Act: -0.1700
Data Index: 5932772 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3083. Min Range: -7.3083
Max Act: 6.8708. Min Act: -0.1700
Data Index: 2758718 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3083. Min Range: -7.3083
Max Act: 6.8395. Min Act: -0.1700
Data Index: 7190996 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3083. Min Range: -7.3083
Max Act: 6.8395. Min Act: -0.1700
Data Index: 5393266 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3083. Min Range: -7.3083
Max Act: 6.8083. Min Act: -0.1700
Data Index: 8787108 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3083. Min Range: -7.3083
Max Act: 6.7770. Min Act: -0.1700
Data Index: 1747575 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3083. Min Range: -7.3083
Max Act: 6.8083. Min Act: -0.1700
Data Index: 2354524 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3083. Min Range: -7.3083
Max Act: 6.7458. Min Act: -0.1700
Data Index: 3970671 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3083. Min Range: -7.3083
Max Act: 6.7458. Min Act: -0.1700
Data Index: 4124261 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3083. Min Range: -7.3083
Max Act: 6.7145. Min Act: -0.1700
Data Index: 3869240 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3083. Min Range: -7.3083
Max Act: 6.7145. Min Act: -0.1700
Data Index: 4023987 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3083. Min Range: -7.3083
Max Act: 6.7145. Min Act: -0.1700
Data Index: 921674 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3083. Min Range: -7.3083
Max Act: 6.7145. Min Act: -0.1700
Data Index: 3422962 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3083. Min Range: -7.3083
Max Act: 6.7145. Min Act: -0.1700
Data Index: 5121550 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19