Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6328 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1264. Min Range: -7.1264
Max Act: 7.1264. Min Act: -0.1700
Data Index: 2566358 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1264. Min Range: -7.1264
Max Act: 7.1264. Min Act: -0.1700
Data Index: 1218833 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1264. Min Range: -7.1264
Max Act: 7.1264. Min Act: -0.1700
Data Index: 5944121 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1264. Min Range: -7.1264
Max Act: 7.0327. Min Act: -0.1700
Data Index: 6932634 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1264. Min Range: -7.1264
Max Act: 7.0327. Min Act: -0.1700
Data Index: 2646503 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1264. Min Range: -7.1264
Max Act: 6.9389. Min Act: -0.1700
Data Index: 431424 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1264. Min Range: -7.1264
Max Act: 6.8764. Min Act: -0.1700
Data Index: 719685 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1264. Min Range: -7.1264
Max Act: 6.8764. Min Act: -0.1700
Data Index: 2661108 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1264. Min Range: -7.1264
Max Act: 6.8764. Min Act: -0.1700
Data Index: 538004 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1264. Min Range: -7.1264
Max Act: 6.8452. Min Act: -0.1700
Data Index: 8123385 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1264. Min Range: -7.1264
Max Act: 6.8452. Min Act: -0.1700
Data Index: 5298260 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1264. Min Range: -7.1264
Max Act: 6.8139. Min Act: -0.1700
Data Index: 8261524 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1264. Min Range: -7.1264
Max Act: 6.8452. Min Act: -0.1700
Data Index: 4780082 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1264. Min Range: -7.1264
Max Act: 6.8452. Min Act: -0.1700
Data Index: 2857534 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1264. Min Range: -7.1264
Max Act: 6.8452. Min Act: -0.1700
Data Index: 378989 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1264. Min Range: -7.1264
Max Act: 6.8139. Min Act: -0.1700
Data Index: 3784189 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1264. Min Range: -7.1264
Max Act: 6.8139. Min Act: -0.1700
Data Index: 5819739 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1264. Min Range: -7.1264
Max Act: 6.8139. Min Act: -0.1700
Data Index: 8772841 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1264. Min Range: -7.1264
Max Act: 6.7827. Min Act: -0.1700
Data Index: 776971 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1264. Min Range: -7.1264
Max Act: 6.7827. Min Act: -0.1700
Data Index: 7112928 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19