Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3590 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3520. Min Range: -7.3520
Max Act: 7.3520. Min Act: -0.1700
Data Index: 3122477 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3520. Min Range: -7.3520
Max Act: 7.1332. Min Act: -0.1700
Data Index: 1429723 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3520. Min Range: -7.3520
Max Act: 7.0395. Min Act: -0.1700
Data Index: 1551174 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3520. Min Range: -7.3520
Max Act: 6.9770. Min Act: -0.1700
Data Index: 6733802 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3520. Min Range: -7.3520
Max Act: 6.9770. Min Act: -0.1700
Data Index: 2775831 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3520. Min Range: -7.3520
Max Act: 6.9457. Min Act: -0.1700
Data Index: 5275819 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3520. Min Range: -7.3520
Max Act: 6.8520. Min Act: -0.1700
Data Index: 4677340 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3520. Min Range: -7.3520
Max Act: 6.8832. Min Act: -0.1700
Data Index: 3372889 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3520. Min Range: -7.3520
Max Act: 6.8832. Min Act: -0.1700
Data Index: 1839720 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3520. Min Range: -7.3520
Max Act: 6.8520. Min Act: -0.1700
Data Index: 6008178 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3520. Min Range: -7.3520
Max Act: 6.8832. Min Act: -0.1700
Data Index: 8480283 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3520. Min Range: -7.3520
Max Act: 6.8520. Min Act: -0.1700
Data Index: 8817199 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3520. Min Range: -7.3520
Max Act: 6.8207. Min Act: -0.1700
Data Index: 5400929 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3520. Min Range: -7.3520
Max Act: 6.8207. Min Act: -0.1700
Data Index: 3079978 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3520. Min Range: -7.3520
Max Act: 6.7895. Min Act: -0.1700
Data Index: 6664154 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3520. Min Range: -7.3520
Max Act: 6.7270. Min Act: -0.1700
Data Index: 6071020 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3520. Min Range: -7.3520
Max Act: 6.7270. Min Act: -0.1700
Data Index: 4827437 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3520. Min Range: -7.3520
Max Act: 6.6957. Min Act: -0.1700
Data Index: 2159370 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3520. Min Range: -7.3520
Max Act: 6.6957. Min Act: -0.1700
Data Index: 1306535 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3520. Min Range: -7.3520
Max Act: 6.7270. Min Act: -0.1700
Data Index: 6726067 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #19