Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6027 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1965. Min Range: -8.1965
Max Act: 8.1965. Min Act: -0.1700
Data Index: 2742116 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1965. Min Range: -8.1965
Max Act: 8.1340. Min Act: -0.1700
Data Index: 4640261 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1965. Min Range: -8.1965
Max Act: 8.0715. Min Act: -0.1700
Data Index: 6976213 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1965. Min Range: -8.1965
Max Act: 7.9152. Min Act: -0.1700
Data Index: 2119782 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1965. Min Range: -8.1965
Max Act: 7.8840. Min Act: -0.1700
Data Index: 4309919 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1965. Min Range: -8.1965
Max Act: 7.7277. Min Act: -0.1700
Data Index: 6530429 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1965. Min Range: -8.1965
Max Act: 7.6340. Min Act: -0.1700
Data Index: 3421079 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1965. Min Range: -8.1965
Max Act: 7.4777. Min Act: -0.1700
Data Index: 8388282 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1965. Min Range: -8.1965
Max Act: 7.4777. Min Act: -0.1700
Data Index: 4056747 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1965. Min Range: -8.1965
Max Act: 7.4465. Min Act: -0.1700
Data Index: 5833214 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1965. Min Range: -8.1965
Max Act: 7.4152. Min Act: -0.1700
Data Index: 594173 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1965. Min Range: -8.1965
Max Act: 7.3527. Min Act: -0.1700
Data Index: 8331804 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1965. Min Range: -8.1965
Max Act: 7.3527. Min Act: -0.1700
Data Index: 3835792 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1965. Min Range: -8.1965
Max Act: 7.3527. Min Act: -0.1700
Data Index: 1664883 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1965. Min Range: -8.1965
Max Act: 7.3215. Min Act: -0.1700
Data Index: 4778795 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1965. Min Range: -8.1965
Max Act: 7.3215. Min Act: -0.1700
Data Index: 8331803 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1965. Min Range: -8.1965
Max Act: 7.3215. Min Act: -0.1700
Data Index: 3921480 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1965. Min Range: -8.1965
Max Act: 7.3215. Min Act: -0.1700
Data Index: 6784776 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1965. Min Range: -8.1965
Max Act: 7.2902. Min Act: -0.1700
Data Index: 1835881 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1965. Min Range: -8.1965
Max Act: 7.2902. Min Act: -0.1700
Data Index: 38639 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19