Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1670 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6547. Min Range: -7.6547
Max Act: 7.6547. Min Act: -0.1700
Data Index: 3288620 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6547. Min Range: -7.6547
Max Act: 7.4672. Min Act: -0.1700
Data Index: 4598457 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6547. Min Range: -7.6547
Max Act: 7.4047. Min Act: -0.1700
Data Index: 6075908 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6547. Min Range: -7.6547
Max Act: 7.3422. Min Act: -0.1700
Data Index: 4362640 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6547. Min Range: -7.6547
Max Act: 7.2797. Min Act: -0.1700
Data Index: 2182689 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6547. Min Range: -7.6547
Max Act: 7.2797. Min Act: -0.1700
Data Index: 8070531 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6547. Min Range: -7.6547
Max Act: 7.2172. Min Act: -0.1700
Data Index: 5626669 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6547. Min Range: -7.6547
Max Act: 7.1547. Min Act: -0.1700
Data Index: 6075907 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6547. Min Range: -7.6547
Max Act: 7.2172. Min Act: -0.1700
Data Index: 3777850 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6547. Min Range: -7.6547
Max Act: 7.1547. Min Act: -0.1700
Data Index: 1455463 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6547. Min Range: -7.6547
Max Act: 7.1547. Min Act: -0.1700
Data Index: 6729986 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6547. Min Range: -7.6547
Max Act: 7.1547. Min Act: -0.1700
Data Index: 4846598 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6547. Min Range: -7.6547
Max Act: 7.1235. Min Act: -0.1700
Data Index: 669452 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6547. Min Range: -7.6547
Max Act: 7.1235. Min Act: -0.1700
Data Index: 6451096 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6547. Min Range: -7.6547
Max Act: 7.0922. Min Act: -0.1700
Data Index: 8371919 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6547. Min Range: -7.6547
Max Act: 7.0922. Min Act: -0.1700
Data Index: 1102793 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6547. Min Range: -7.6547
Max Act: 7.0922. Min Act: -0.1700
Data Index: 8268433 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6547. Min Range: -7.6547
Max Act: 7.1235. Min Act: -0.1700
Data Index: 2847744 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6547. Min Range: -7.6547
Max Act: 7.0610. Min Act: -0.1700
Data Index: 6677915 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6547. Min Range: -7.6547
Max Act: 7.0610. Min Act: -0.1700
Data Index: 780235 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19