Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2056 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.4680. Min Act: -0.1700
Data Index: 2397291 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.3430. Min Act: -0.1700
Data Index: 2735754 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.3117. Min Act: -0.1700
Data Index: 8037925 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.2180. Min Act: -0.1700
Data Index: 6541714 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.2492. Min Act: -0.1700
Data Index: 938383 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.1555. Min Act: -0.1700
Data Index: 2920107 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.1242. Min Act: -0.1700
Data Index: 7112078 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.1242. Min Act: -0.1700
Data Index: 6650671 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.1242. Min Act: -0.1700
Data Index: 7294094 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.0930. Min Act: -0.1700
Data Index: 4897863 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.1242. Min Act: -0.1700
Data Index: 5670872 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.0617. Min Act: -0.1700
Data Index: 7058451 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.0617. Min Act: -0.1700
Data Index: 5688412 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.0617. Min Act: -0.1700
Data Index: 3977003 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.0617. Min Act: -0.1700
Data Index: 5474354 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.0305. Min Act: -0.1700
Data Index: 225753 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4680. Min Range: -7.4680
Max Act: 6.9992. Min Act: -0.1700
Data Index: 1527978 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.0305. Min Act: -0.1700
Data Index: 5991786 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4680. Min Range: -7.4680
Max Act: 7.0305. Min Act: -0.1700
Data Index: 4752934 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4680. Min Range: -7.4680
Max Act: 6.9680. Min Act: -0.1700
Data Index: 6415363 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #19