Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5400 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3467. Min Range: -9.3467
Max Act: 9.3467. Min Act: -0.1700
Data Index: 6459762 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3467. Min Range: -9.3467
Max Act: 9.0342. Min Act: -0.1700
Data Index: 3431018 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3467. Min Range: -9.3467
Max Act: 8.9717. Min Act: -0.1700
Data Index: 3640610 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3467. Min Range: -9.3467
Max Act: 8.9092. Min Act: -0.1700
Data Index: 4542460 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3467. Min Range: -9.3467
Max Act: 8.7842. Min Act: -0.1700
Data Index: 3110848 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3467. Min Range: -9.3467
Max Act: 8.6592. Min Act: -0.1700
Data Index: 499680 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3467. Min Range: -9.3467
Max Act: 8.5342. Min Act: -0.1700
Data Index: 5559456 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3467. Min Range: -9.3467
Max Act: 8.5342. Min Act: -0.1700
Data Index: 8509318 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3467. Min Range: -9.3467
Max Act: 8.5342. Min Act: -0.1700
Data Index: 3102717 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3467. Min Range: -9.3467
Max Act: 8.4717. Min Act: -0.1700
Data Index: 4970655 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3467. Min Range: -9.3467
Max Act: 8.4092. Min Act: -0.1699
Data Index: 8398204 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3467. Min Range: -9.3467
Max Act: 8.4092. Min Act: -0.1700
Data Index: 6459761 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3467. Min Range: -9.3467
Max Act: 8.3467. Min Act: -0.1700
Data Index: 7598944 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3467. Min Range: -9.3467
Max Act: 8.3467. Min Act: -0.1700
Data Index: 4570195 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3467. Min Range: -9.3467
Max Act: 8.3467. Min Act: -0.1700
Data Index: 1392691 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3467. Min Range: -9.3467
Max Act: 8.2842. Min Act: -0.1700
Data Index: 5326365 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3467. Min Range: -9.3467
Max Act: 8.2842. Min Act: -0.1700
Data Index: 2782947 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3467. Min Range: -9.3467
Max Act: 8.2217. Min Act: -0.1700
Data Index: 7560289 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3467. Min Range: -9.3467
Max Act: 8.2217. Min Act: -0.1700
Data Index: 91150 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3467. Min Range: -9.3467
Max Act: 8.2842. Min Act: -0.1700
Data Index: 5325345 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #19