Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2802 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1192. Min Range: -7.1192
Max Act: 7.1192. Min Act: -0.1700
Data Index: 1996355 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1192. Min Range: -7.1192
Max Act: 6.7442. Min Act: -0.1700
Data Index: 4045426 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1192. Min Range: -7.1192
Max Act: 6.7129. Min Act: -0.1700
Data Index: 4073022 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1192. Min Range: -7.1192
Max Act: 6.6817. Min Act: -0.1700
Data Index: 2919611 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1192. Min Range: -7.1192
Max Act: 6.6192. Min Act: -0.1700
Data Index: 8768814 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1192. Min Range: -7.1192
Max Act: 6.5879. Min Act: -0.1700
Data Index: 1499602 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1192. Min Range: -7.1192
Max Act: 6.4317. Min Act: -0.1700
Data Index: 4651703 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1192. Min Range: -7.1192
Max Act: 6.4317. Min Act: -0.1700
Data Index: 8045987 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1192. Min Range: -7.1192
Max Act: 6.4004. Min Act: -0.1700
Data Index: 4288437 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1192. Min Range: -7.1192
Max Act: 6.3692. Min Act: -0.1700
Data Index: 1006624 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1192. Min Range: -7.1192
Max Act: 6.3067. Min Act: -0.1700
Data Index: 1782576 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1192. Min Range: -7.1192
Max Act: 6.3067. Min Act: -0.1700
Data Index: 315124 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1192. Min Range: -7.1192
Max Act: 6.2754. Min Act: -0.1700
Data Index: 6897023 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1192. Min Range: -7.1192
Max Act: 6.2754. Min Act: -0.1700
Data Index: 4781835 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1192. Min Range: -7.1192
Max Act: 6.2442. Min Act: -0.1700
Data Index: 5758632 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1192. Min Range: -7.1192
Max Act: 6.2442. Min Act: -0.1700
Data Index: 5454507 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1192. Min Range: -7.1192
Max Act: 6.2129. Min Act: -0.1700
Data Index: 3904319 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1192. Min Range: -7.1192
Max Act: 6.1817. Min Act: -0.1700
Data Index: 5260500 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1192. Min Range: -7.1192
Max Act: 6.1817. Min Act: -0.1700
Data Index: 4407047 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1192. Min Range: -7.1192
Max Act: 6.1817. Min Act: -0.1700
Data Index: 928834 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19