Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3026 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3906. Min Range: -5.3906
Max Act: 5.3906. Min Act: -0.1700
Data Index: 4952089 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3906. Min Range: -5.3906
Max Act: 5.2031. Min Act: -0.1700
Data Index: 5625319 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3906. Min Range: -5.3906
Max Act: 5.2031. Min Act: -0.1700
Data Index: 2306015 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3906. Min Range: -5.3906
Max Act: 5.1719. Min Act: -0.1700
Data Index: 7146869 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3906. Min Range: -5.3906
Max Act: 5.1406. Min Act: -0.1700
Data Index: 4386107 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3906. Min Range: -5.3906
Max Act: 5.1406. Min Act: -0.1700
Data Index: 1028641 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3906. Min Range: -5.3906
Max Act: 5.1094. Min Act: -0.1700
Data Index: 7703857 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3906. Min Range: -5.3906
Max Act: 5.1094. Min Act: -0.1700
Data Index: 8477245 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3906. Min Range: -5.3906
Max Act: 5.1094. Min Act: -0.1700
Data Index: 5042268 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3906. Min Range: -5.3906
Max Act: 5.1094. Min Act: -0.1700
Data Index: 1210449 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3906. Min Range: -5.3906
Max Act: 5.1094. Min Act: -0.1700
Data Index: 8564096 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3906. Min Range: -5.3906
Max Act: 5.1094. Min Act: -0.1700
Data Index: 7610104 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3906. Min Range: -5.3906
Max Act: 5.0781. Min Act: -0.1700
Data Index: 6107506 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3906. Min Range: -5.3906
Max Act: 5.0781. Min Act: -0.1700
Data Index: 2242416 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3906. Min Range: -5.3906
Max Act: 5.0781. Min Act: -0.1700
Data Index: 6760115 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3906. Min Range: -5.3906
Max Act: 5.0781. Min Act: -0.1700
Data Index: 7277253 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3906. Min Range: -5.3906
Max Act: 5.0469. Min Act: -0.1700
Data Index: 6471702 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3906. Min Range: -5.3906
Max Act: 5.0469. Min Act: -0.1700
Data Index: 5216431 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3906. Min Range: -5.3906
Max Act: 5.0156. Min Act: -0.1700
Data Index: 3004706 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3906. Min Range: -5.3906
Max Act: 4.9844. Min Act: -0.1700
Data Index: 8381632 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #19