Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 596 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1906. Min Range: -6.1906
Max Act: 6.1906. Min Act: -0.1700
Data Index: 5986083 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1906. Min Range: -6.1906
Max Act: 5.9719. Min Act: -0.1700
Data Index: 5398578 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1906. Min Range: -6.1906
Max Act: 5.8469. Min Act: -0.1700
Data Index: 3104631 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1906. Min Range: -6.1906
Max Act: 5.8469. Min Act: -0.1700
Data Index: 4660743 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1906. Min Range: -6.1906
Max Act: 5.7531. Min Act: -0.1700
Data Index: 6433503 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1906. Min Range: -6.1906
Max Act: 5.7219. Min Act: -0.1700
Data Index: 2459427 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1906. Min Range: -6.1906
Max Act: 5.6906. Min Act: -0.1700
Data Index: 7324464 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1906. Min Range: -6.1906
Max Act: 5.7219. Min Act: -0.1700
Data Index: 1360127 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1906. Min Range: -6.1906
Max Act: 5.6906. Min Act: -0.1700
Data Index: 2744728 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1906. Min Range: -6.1906
Max Act: 5.6906. Min Act: -0.1700
Data Index: 6406296 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1906. Min Range: -6.1906
Max Act: 5.6594. Min Act: -0.1700
Data Index: 6902155 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1906. Min Range: -6.1906
Max Act: 5.6594. Min Act: -0.1700
Data Index: 8655490 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1906. Min Range: -6.1906
Max Act: 5.6594. Min Act: -0.1700
Data Index: 1737310 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1906. Min Range: -6.1906
Max Act: 5.6281. Min Act: -0.1700
Data Index: 4728602 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1906. Min Range: -6.1906
Max Act: 5.6281. Min Act: -0.1700
Data Index: 2419579 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1906. Min Range: -6.1906
Max Act: 5.6281. Min Act: -0.1700
Data Index: 2637507 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1906. Min Range: -6.1906
Max Act: 5.6281. Min Act: -0.1700
Data Index: 6941489 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1906. Min Range: -6.1906
Max Act: 5.5969. Min Act: -0.1700
Data Index: 560320 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1906. Min Range: -6.1906
Max Act: 5.5969. Min Act: -0.1700
Data Index: 8260738 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1906. Min Range: -6.1906
Max Act: 5.5969. Min Act: -0.1700
Data Index: 1681504 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19