Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4805 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8542. Min Range: -6.8542
Max Act: 6.8542. Min Act: -0.1700
Data Index: 8709696 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8542. Min Range: -6.8542
Max Act: 6.7605. Min Act: -0.1700
Data Index: 4399931 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8542. Min Range: -6.8542
Max Act: 6.6980. Min Act: -0.1700
Data Index: 6105194 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8542. Min Range: -6.8542
Max Act: 6.6980. Min Act: -0.1700
Data Index: 7096472 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8542. Min Range: -6.8542
Max Act: 6.6667. Min Act: -0.1700
Data Index: 4476448 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8542. Min Range: -6.8542
Max Act: 6.6667. Min Act: -0.1700
Data Index: 591818 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8542. Min Range: -6.8542
Max Act: 6.5730. Min Act: -0.1700
Data Index: 2566160 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8542. Min Range: -6.8542
Max Act: 6.5730. Min Act: -0.1700
Data Index: 161846 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8542. Min Range: -6.8542
Max Act: 6.4792. Min Act: -0.1700
Data Index: 6126010 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8542. Min Range: -6.8542
Max Act: 6.5417. Min Act: -0.1700
Data Index: 8075196 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8542. Min Range: -6.8542
Max Act: 6.4792. Min Act: -0.1700
Data Index: 8257886 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8542. Min Range: -6.8542
Max Act: 6.4480. Min Act: -0.1700
Data Index: 8419752 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8542. Min Range: -6.8542
Max Act: 6.4792. Min Act: -0.1700
Data Index: 2496820 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8542. Min Range: -6.8542
Max Act: 6.3855. Min Act: -0.1700
Data Index: 4893436 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8542. Min Range: -6.8542
Max Act: 6.3855. Min Act: -0.1700
Data Index: 6079274 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8542. Min Range: -6.8542
Max Act: 6.4167. Min Act: -0.1700
Data Index: 7136282 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8542. Min Range: -6.8542
Max Act: 6.3542. Min Act: -0.1700
Data Index: 3163431 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8542. Min Range: -6.8542
Max Act: 6.3230. Min Act: -0.1700
Data Index: 7634758 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8542. Min Range: -6.8542
Max Act: 6.3230. Min Act: -0.1700
Data Index: 2373546 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8542. Min Range: -6.8542
Max Act: 6.3230. Min Act: -0.1700
Data Index: 7808290 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19