Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3705 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3791. Min Range: -5.3791
Max Act: 5.3791. Min Act: -0.1700
Data Index: 34145 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3791. Min Range: -5.3791
Max Act: 5.2541. Min Act: -0.1700
Data Index: 6061514 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3791. Min Range: -5.3791
Max Act: 5.1916. Min Act: -0.1700
Data Index: 3351622 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3791. Min Range: -5.3791
Max Act: 5.1604. Min Act: -0.1700
Data Index: 8100958 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3791. Min Range: -5.3791
Max Act: 5.0979. Min Act: -0.1700
Data Index: 5461604 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3791. Min Range: -5.3791
Max Act: 5.0354. Min Act: -0.1700
Data Index: 2913383 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3791. Min Range: -5.3791
Max Act: 5.0354. Min Act: -0.1700
Data Index: 4506486 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3791. Min Range: -5.3791
Max Act: 5.0354. Min Act: -0.1700
Data Index: 624079 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3791. Min Range: -5.3791
Max Act: 5.0354. Min Act: -0.1700
Data Index: 5328148 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3791. Min Range: -5.3791
Max Act: 5.0041. Min Act: -0.1700
Data Index: 4450619 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3791. Min Range: -5.3791
Max Act: 5.0041. Min Act: -0.1700
Data Index: 6392857 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3791. Min Range: -5.3791
Max Act: 4.8479. Min Act: -0.1700
Data Index: 5056071 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3791. Min Range: -5.3791
Max Act: 4.7541. Min Act: -0.1700
Data Index: 7851416 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3791. Min Range: -5.3791
Max Act: 4.7229. Min Act: -0.1700
Data Index: 3018507 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3791. Min Range: -5.3791
Max Act: 4.6916. Min Act: -0.1700
Data Index: 4882507 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3791. Min Range: -5.3791
Max Act: 4.6916. Min Act: -0.1700
Data Index: 4930440 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3791. Min Range: -5.3791
Max Act: 4.6916. Min Act: -0.1700
Data Index: 269684 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3791. Min Range: -5.3791
Max Act: 4.6291. Min Act: -0.1700
Data Index: 1950902 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3791. Min Range: -5.3791
Max Act: 4.5979. Min Act: -0.1700
Data Index: 7141649 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3791. Min Range: -5.3791
Max Act: 4.5979. Min Act: -0.1700
Data Index: 3601242 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #19