Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4501 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3786. Min Range: -5.3786
Max Act: 5.3786. Min Act: -0.1700
Data Index: 3962880 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3786. Min Range: -5.3786
Max Act: 5.1286. Min Act: -0.1700
Data Index: 4499498 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3786. Min Range: -5.3786
Max Act: 5.0973. Min Act: -0.1700
Data Index: 3723466 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3786. Min Range: -5.3786
Max Act: 5.0973. Min Act: -0.1700
Data Index: 4499497 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3786. Min Range: -5.3786
Max Act: 4.9723. Min Act: -0.1700
Data Index: 6768751 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3786. Min Range: -5.3786
Max Act: 4.8786. Min Act: -0.1700
Data Index: 7013687 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3786. Min Range: -5.3786
Max Act: 4.8161. Min Act: -0.1700
Data Index: 3253364 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3786. Min Range: -5.3786
Max Act: 4.7536. Min Act: -0.1700
Data Index: 6768754 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3786. Min Range: -5.3786
Max Act: 4.7848. Min Act: -0.1700
Data Index: 7924295 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3786. Min Range: -5.3786
Max Act: 4.7223. Min Act: -0.1700
Data Index: 4173613 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3786. Min Range: -5.3786
Max Act: 4.7536. Min Act: -0.1700
Data Index: 8382358 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3786. Min Range: -5.3786
Max Act: 4.7223. Min Act: -0.1700
Data Index: 640729 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3786. Min Range: -5.3786
Max Act: 4.6910. Min Act: -0.1700
Data Index: 4360164 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3786. Min Range: -5.3786
Max Act: 4.6910. Min Act: -0.1700
Data Index: 5328056 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3786. Min Range: -5.3786
Max Act: 4.7223. Min Act: -0.1700
Data Index: 3022090 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3786. Min Range: -5.3786
Max Act: 4.6910. Min Act: -0.1700
Data Index: 5673856 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3786. Min Range: -5.3786
Max Act: 4.6910. Min Act: -0.1700
Data Index: 4378718 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3786. Min Range: -5.3786
Max Act: 4.6598. Min Act: -0.1700
Data Index: 2971838 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3786. Min Range: -5.3786
Max Act: 4.6598. Min Act: -0.1700
Data Index: 5899191 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3786. Min Range: -5.3786
Max Act: 4.6910. Min Act: -0.1700
Data Index: 926963 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19