Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2958 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7373. Min Range: -4.7373
Max Act: 4.7373. Min Act: -0.1700
Data Index: 6971852 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7373. Min Range: -4.7373
Max Act: 4.5498. Min Act: -0.1700
Data Index: 6140503 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7373. Min Range: -4.7373
Max Act: 4.4560. Min Act: -0.1700
Data Index: 2606903 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7373. Min Range: -4.7373
Max Act: 4.4873. Min Act: -0.1700
Data Index: 1957538 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7373. Min Range: -4.7373
Max Act: 4.4248. Min Act: -0.1700
Data Index: 756811 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7373. Min Range: -4.7373
Max Act: 4.3935. Min Act: -0.1700
Data Index: 6391331 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7373. Min Range: -4.7373
Max Act: 4.3623. Min Act: -0.1700
Data Index: 2701757 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7373. Min Range: -4.7373
Max Act: 4.3935. Min Act: -0.1700
Data Index: 4768028 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7373. Min Range: -4.7373
Max Act: 4.3935. Min Act: -0.1700
Data Index: 3846710 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7373. Min Range: -4.7373
Max Act: 4.3623. Min Act: -0.1700
Data Index: 6140499 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7373. Min Range: -4.7373
Max Act: 4.3935. Min Act: -0.1700
Data Index: 4018987 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7373. Min Range: -4.7373
Max Act: 4.3310. Min Act: -0.1700
Data Index: 8256301 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7373. Min Range: -4.7373
Max Act: 4.3310. Min Act: -0.1700
Data Index: 740780 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7373. Min Range: -4.7373
Max Act: 4.3623. Min Act: -0.1700
Data Index: 336725 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7373. Min Range: -4.7373
Max Act: 4.3623. Min Act: -0.1700
Data Index: 6488066 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7373. Min Range: -4.7373
Max Act: 4.3623. Min Act: -0.1700
Data Index: 6515183 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7373. Min Range: -4.7373
Max Act: 4.3623. Min Act: -0.1700
Data Index: 5069550 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7373. Min Range: -4.7373
Max Act: 4.3623. Min Act: -0.1700
Data Index: 2315798 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7373. Min Range: -4.7373
Max Act: 4.3623. Min Act: -0.1700
Data Index: 6479728 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7373. Min Range: -4.7373
Max Act: 4.3310. Min Act: -0.1700
Data Index: 6327123 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19