Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1684 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.4462. Min Act: -0.1700
Data Index: 668739 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.2899. Min Act: -0.1700
Data Index: 668740 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.2899. Min Act: -0.1700
Data Index: 1501769 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.2587. Min Act: -0.1700
Data Index: 8392885 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.2587. Min Act: -0.1700
Data Index: 6285437 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.1962. Min Act: -0.1700
Data Index: 659395 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.1962. Min Act: -0.1700
Data Index: 3203436 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.1962. Min Act: -0.1700
Data Index: 6737000 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.1962. Min Act: -0.1700
Data Index: 8095098 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.1649. Min Act: -0.1700
Data Index: 7603054 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.1337. Min Act: -0.1700
Data Index: 2152122 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.1024. Min Act: -0.1700
Data Index: 8786511 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.1024. Min Act: -0.1700
Data Index: 1978834 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.0399. Min Act: -0.1700
Data Index: 7278968 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.0399. Min Act: -0.1700
Data Index: 1978835 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.0399. Min Act: -0.1700
Data Index: 2715658 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.0399. Min Act: -0.1700
Data Index: 5374464 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.0399. Min Act: -0.1700
Data Index: 3050823 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4462. Min Range: -5.4462
Max Act: 5.0087. Min Act: -0.1700
Data Index: 6481634 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4462. Min Range: -5.4462
Max Act: 4.9774. Min Act: -0.1700
Data Index: 6285431 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19