Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5776 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4907. Min Range: -6.4907
Max Act: 6.4907. Min Act: -0.1700
Data Index: 7209986 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4907. Min Range: -6.4907
Max Act: 6.4282. Min Act: -0.1700
Data Index: 972839 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4907. Min Range: -6.4907
Max Act: 6.4282. Min Act: -0.1700
Data Index: 5494097 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4907. Min Range: -6.4907
Max Act: 6.4282. Min Act: -0.1700
Data Index: 2570802 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4907. Min Range: -6.4907
Max Act: 6.3970. Min Act: -0.1700
Data Index: 5973119 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4907. Min Range: -6.4907
Max Act: 6.3345. Min Act: -0.1700
Data Index: 8470418 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4907. Min Range: -6.4907
Max Act: 6.3032. Min Act: -0.1700
Data Index: 2560162 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4907. Min Range: -6.4907
Max Act: 6.2407. Min Act: -0.1700
Data Index: 3846445 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4907. Min Range: -6.4907
Max Act: 6.2407. Min Act: -0.1700
Data Index: 5880827 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4907. Min Range: -6.4907
Max Act: 6.2407. Min Act: -0.1700
Data Index: 6442794 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4907. Min Range: -6.4907
Max Act: 6.2095. Min Act: -0.1700
Data Index: 8364994 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4907. Min Range: -6.4907
Max Act: 6.1470. Min Act: -0.1700
Data Index: 2134210 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4907. Min Range: -6.4907
Max Act: 6.1782. Min Act: -0.1700
Data Index: 6685580 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4907. Min Range: -6.4907
Max Act: 6.1470. Min Act: -0.1700
Data Index: 1316068 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4907. Min Range: -6.4907
Max Act: 6.1470. Min Act: -0.1700
Data Index: 5683020 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4907. Min Range: -6.4907
Max Act: 6.1157. Min Act: -0.1700
Data Index: 3694716 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4907. Min Range: -6.4907
Max Act: 6.1157. Min Act: -0.1700
Data Index: 1340980 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4907. Min Range: -6.4907
Max Act: 6.1157. Min Act: -0.1700
Data Index: 6109808 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4907. Min Range: -6.4907
Max Act: 6.1157. Min Act: -0.1700
Data Index: 2617013 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4907. Min Range: -6.4907
Max Act: 6.0845. Min Act: -0.1700
Data Index: 5901054 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19