Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3984 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0883. Min Range: -5.0883
Max Act: 5.0883. Min Act: -0.1700
Data Index: 762267 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0883. Min Range: -5.0883
Max Act: 4.9946. Min Act: -0.1700
Data Index: 5740372 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0883. Min Range: -5.0883
Max Act: 4.9946. Min Act: -0.1700
Data Index: 3818945 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0883. Min Range: -5.0883
Max Act: 4.9946. Min Act: -0.1700
Data Index: 2455179 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0883. Min Range: -5.0883
Max Act: 4.9633. Min Act: -0.1700
Data Index: 3337172 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0883. Min Range: -5.0883
Max Act: 4.9321. Min Act: -0.1700
Data Index: 5110169 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0883. Min Range: -5.0883
Max Act: 4.9008. Min Act: -0.1700
Data Index: 373766 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0883. Min Range: -5.0883
Max Act: 4.9008. Min Act: -0.1700
Data Index: 4993845 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0883. Min Range: -5.0883
Max Act: 4.9008. Min Act: -0.1700
Data Index: 5402155 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0883. Min Range: -5.0883
Max Act: 4.9008. Min Act: -0.1700
Data Index: 3458669 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0883. Min Range: -5.0883
Max Act: 4.8696. Min Act: -0.1700
Data Index: 1674687 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0883. Min Range: -5.0883
Max Act: 4.8696. Min Act: -0.1700
Data Index: 741452 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0883. Min Range: -5.0883
Max Act: 4.8696. Min Act: -0.1700
Data Index: 5936385 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0883. Min Range: -5.0883
Max Act: 4.8696. Min Act: -0.1700
Data Index: 6106173 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0883. Min Range: -5.0883
Max Act: 4.8383. Min Act: -0.1700
Data Index: 5448511 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0883. Min Range: -5.0883
Max Act: 4.8383. Min Act: -0.1700
Data Index: 2481806 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0883. Min Range: -5.0883
Max Act: 4.8383. Min Act: -0.1700
Data Index: 5932816 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0883. Min Range: -5.0883
Max Act: 4.8071. Min Act: -0.1700
Data Index: 1196595 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0883. Min Range: -5.0883
Max Act: 4.8071. Min Act: -0.1700
Data Index: 1492941 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0883. Min Range: -5.0883
Max Act: 4.8071. Min Act: -0.1700
Data Index: 6757988 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #19