Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1664 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4813. Min Range: -9.4813
Max Act: 9.4813. Min Act: -0.1700
Data Index: 1866020 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4813. Min Range: -9.4813
Max Act: 9.3563. Min Act: -0.1700
Data Index: 7796544 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4813. Min Range: -9.4813
Max Act: 9.2938. Min Act: -0.1700
Data Index: 4742049 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4813. Min Range: -9.4813
Max Act: 9.1688. Min Act: -0.1700
Data Index: 5717654 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4813. Min Range: -9.4813
Max Act: 9.0438. Min Act: -0.1700
Data Index: 6911292 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4813. Min Range: -9.4813
Max Act: 9.0438. Min Act: -0.1700
Data Index: 879821 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4813. Min Range: -9.4813
Max Act: 8.9813. Min Act: -0.1700
Data Index: 5232718 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4813. Min Range: -9.4813
Max Act: 8.9188. Min Act: -0.1700
Data Index: 7031961 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4813. Min Range: -9.4813
Max Act: 8.9188. Min Act: -0.1700
Data Index: 6635158 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4813. Min Range: -9.4813
Max Act: 8.9188. Min Act: -0.1700
Data Index: 7761827 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4813. Min Range: -9.4813
Max Act: 8.7938. Min Act: -0.1700
Data Index: 4828850 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4813. Min Range: -9.4813
Max Act: 8.7938. Min Act: -0.1700
Data Index: 2112183 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4813. Min Range: -9.4813
Max Act: 8.7938. Min Act: -0.1700
Data Index: 4637850 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4813. Min Range: -9.4813
Max Act: 8.6688. Min Act: -0.1700
Data Index: 7042085 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4813. Min Range: -9.4813
Max Act: 8.5438. Min Act: -0.1700
Data Index: 4215832 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4813. Min Range: -9.4813
Max Act: 8.5438. Min Act: -0.1700
Data Index: 1156198 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4813. Min Range: -9.4813
Max Act: 8.5438. Min Act: -0.1700
Data Index: 4407860 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4813. Min Range: -9.4813
Max Act: 8.4813. Min Act: -0.1700
Data Index: 7228394 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4813. Min Range: -9.4813
Max Act: 8.4188. Min Act: -0.1700
Data Index: 5010390 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4813. Min Range: -9.4813
Max Act: 8.4813. Min Act: -0.1700
Data Index: 3529494 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19