Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4214 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.2164. Min Act: -0.1700
Data Index: 2073845 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.1692. Min Act: -0.1700
Data Index: 2403284 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.1692. Min Act: -0.1700
Data Index: 3885997 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.1377. Min Act: -0.1700
Data Index: 5305092 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.1377. Min Act: -0.1700
Data Index: 7861038 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.1377. Min Act: -0.1700
Data Index: 5100130 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.1062. Min Act: -0.1700
Data Index: 7468695 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.0747. Min Act: -0.1700
Data Index: 3961053 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.1062. Min Act: -0.1700
Data Index: 799985 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.0589. Min Act: -0.1700
Data Index: 5100923 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.0589. Min Act: -0.1700
Data Index: 4729049 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.0904. Min Act: -0.1700
Data Index: 7239442 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.0431. Min Act: -0.1700
Data Index: 1209154 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.0431. Min Act: -0.1700
Data Index: 5262377 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.0589. Min Act: -0.1700
Data Index: 3001023 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.0431. Min Act: -0.1700
Data Index: 8061837 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.0747. Min Act: -0.1700
Data Index: 5332906 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.0273. Min Act: -0.1700
Data Index: 4176694 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.0115. Min Act: -0.1700
Data Index: 3075926 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2164. Min Range: -3.2164
Max Act: 3.0273. Min Act: -0.1700
Data Index: 5667536 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19