Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4889 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7894. Min Range: -5.7894
Max Act: 5.7894. Min Act: -0.1700
Data Index: 1782472 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7894. Min Range: -5.7894
Max Act: 5.7582. Min Act: -0.1700
Data Index: 8790080 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7894. Min Range: -5.7894
Max Act: 5.4769. Min Act: -0.1700
Data Index: 8740134 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7894. Min Range: -5.7894
Max Act: 5.3519. Min Act: -0.1700
Data Index: 6176348 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7894. Min Range: -5.7894
Max Act: 5.3519. Min Act: -0.1700
Data Index: 108881 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7894. Min Range: -5.7894
Max Act: 5.3207. Min Act: -0.1700
Data Index: 5316451 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7894. Min Range: -5.7894
Max Act: 5.3207. Min Act: -0.1700
Data Index: 6702317 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7894. Min Range: -5.7894
Max Act: 5.3207. Min Act: -0.1700
Data Index: 5573443 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7894. Min Range: -5.7894
Max Act: 5.2894. Min Act: -0.1700
Data Index: 2369722 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7894. Min Range: -5.7894
Max Act: 5.2894. Min Act: -0.1700
Data Index: 6859495 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7894. Min Range: -5.7894
Max Act: 5.2582. Min Act: -0.1700
Data Index: 7659658 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7894. Min Range: -5.7894
Max Act: 5.2582. Min Act: -0.1700
Data Index: 5679423 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7894. Min Range: -5.7894
Max Act: 5.2582. Min Act: -0.1700
Data Index: 3838547 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7894. Min Range: -5.7894
Max Act: 5.2582. Min Act: -0.1700
Data Index: 1429909 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7894. Min Range: -5.7894
Max Act: 5.2582. Min Act: -0.1700
Data Index: 1331175 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7894. Min Range: -5.7894
Max Act: 5.2582. Min Act: -0.1700
Data Index: 6776304 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7894. Min Range: -5.7894
Max Act: 5.2582. Min Act: -0.1700
Data Index: 6550219 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7894. Min Range: -5.7894
Max Act: 5.2269. Min Act: -0.1700
Data Index: 1512335 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7894. Min Range: -5.7894
Max Act: 5.2269. Min Act: -0.1700
Data Index: 2751352 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7894. Min Range: -5.7894
Max Act: 5.2269. Min Act: -0.1700
Data Index: 884657 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19