Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3060 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9668. Min Range: -4.9668
Max Act: 4.9668. Min Act: -0.1700
Data Index: 7692842 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9668. Min Range: -4.9668
Max Act: 4.9355. Min Act: -0.1700
Data Index: 8298876 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9668. Min Range: -4.9668
Max Act: 4.9043. Min Act: -0.1700
Data Index: 3296086 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9668. Min Range: -4.9668
Max Act: 4.8418. Min Act: -0.1700
Data Index: 6555582 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9668. Min Range: -4.9668
Max Act: 4.8418. Min Act: -0.1700
Data Index: 2575363 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9668. Min Range: -4.9668
Max Act: 4.8418. Min Act: -0.1700
Data Index: 3195575 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9668. Min Range: -4.9668
Max Act: 4.8418. Min Act: -0.1700
Data Index: 8247848 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9668. Min Range: -4.9668
Max Act: 4.8105. Min Act: -0.1700
Data Index: 5493842 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9668. Min Range: -4.9668
Max Act: 4.8418. Min Act: -0.1700
Data Index: 2506646 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9668. Min Range: -4.9668
Max Act: 4.8105. Min Act: -0.1700
Data Index: 4850017 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9668. Min Range: -4.9668
Max Act: 4.8105. Min Act: -0.1700
Data Index: 39829 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9668. Min Range: -4.9668
Max Act: 4.7793. Min Act: -0.1700
Data Index: 2863268 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9668. Min Range: -4.9668
Max Act: 4.7480. Min Act: -0.1700
Data Index: 1372341 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9668. Min Range: -4.9668
Max Act: 4.7793. Min Act: -0.1700
Data Index: 1434940 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9668. Min Range: -4.9668
Max Act: 4.8105. Min Act: -0.1700
Data Index: 3009707 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9668. Min Range: -4.9668
Max Act: 4.7793. Min Act: -0.1700
Data Index: 7538810 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9668. Min Range: -4.9668
Max Act: 4.7480. Min Act: -0.1700
Data Index: 3906467 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9668. Min Range: -4.9668
Max Act: 4.7480. Min Act: -0.1700
Data Index: 2244768 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9668. Min Range: -4.9668
Max Act: 4.7480. Min Act: -0.1700
Data Index: 5379759 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9668. Min Range: -4.9668
Max Act: 4.7168. Min Act: -0.1700
Data Index: 5856575 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19