Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3003 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6802. Min Range: -6.6802
Max Act: 6.6802. Min Act: -0.1700
Data Index: 5014422 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6802. Min Range: -6.6802
Max Act: 6.6489. Min Act: -0.1700
Data Index: 864224 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6802. Min Range: -6.6802
Max Act: 6.2427. Min Act: -0.1700
Data Index: 955582 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6802. Min Range: -6.6802
Max Act: 6.1489. Min Act: -0.1700
Data Index: 2042496 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6802. Min Range: -6.6802
Max Act: 6.1177. Min Act: -0.1700
Data Index: 3117409 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6802. Min Range: -6.6802
Max Act: 6.0552. Min Act: -0.1700
Data Index: 6135420 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6802. Min Range: -6.6802
Max Act: 6.0552. Min Act: -0.1700
Data Index: 1751277 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6802. Min Range: -6.6802
Max Act: 6.0552. Min Act: -0.1700
Data Index: 4487224 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6802. Min Range: -6.6802
Max Act: 6.0239. Min Act: -0.1700
Data Index: 7715280 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6802. Min Range: -6.6802
Max Act: 6.0239. Min Act: -0.1700
Data Index: 4388189 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6802. Min Range: -6.6802
Max Act: 6.0239. Min Act: -0.1700
Data Index: 1314925 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6802. Min Range: -6.6802
Max Act: 6.0239. Min Act: -0.1700
Data Index: 7078035 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6802. Min Range: -6.6802
Max Act: 5.9614. Min Act: -0.1700
Data Index: 3932111 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6802. Min Range: -6.6802
Max Act: 5.9927. Min Act: -0.1700
Data Index: 6519043 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6802. Min Range: -6.6802
Max Act: 5.9614. Min Act: -0.1700
Data Index: 4479391 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6802. Min Range: -6.6802
Max Act: 5.9614. Min Act: -0.1700
Data Index: 1714140 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6802. Min Range: -6.6802
Max Act: 5.9302. Min Act: -0.1700
Data Index: 5530958 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6802. Min Range: -6.6802
Max Act: 5.9614. Min Act: -0.1700
Data Index: 1805525 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6802. Min Range: -6.6802
Max Act: 5.9302. Min Act: -0.1700
Data Index: 8802096 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6802. Min Range: -6.6802
Max Act: 5.9302. Min Act: -0.1700
Data Index: 825159 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19