Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5876 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0365. Min Range: -5.0365
Max Act: 5.0365. Min Act: -0.1700
Data Index: 1535350 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0365. Min Range: -5.0365
Max Act: 5.0365. Min Act: -0.1700
Data Index: 6708394 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0365. Min Range: -5.0365
Max Act: 5.0053. Min Act: -0.1700
Data Index: 5540570 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.9740. Min Act: -0.1700
Data Index: 5540571 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.8803. Min Act: -0.1700
Data Index: 4262089 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.8490. Min Act: -0.1700
Data Index: 310500 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.8178. Min Act: -0.1700
Data Index: 5966801 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.8178. Min Act: -0.1700
Data Index: 6906495 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.7865. Min Act: -0.1700
Data Index: 1795693 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.7865. Min Act: -0.1700
Data Index: 4341061 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.7553. Min Act: -0.1700
Data Index: 782997 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.7553. Min Act: -0.1700
Data Index: 6358808 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.7240. Min Act: -0.1700
Data Index: 357038 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.7240. Min Act: -0.1700
Data Index: 6938707 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.7240. Min Act: -0.1700
Data Index: 8770649 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.6928. Min Act: -0.1700
Data Index: 1662198 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.7240. Min Act: -0.1700
Data Index: 3508243 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.6928. Min Act: -0.1700
Data Index: 7847545 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.7240. Min Act: -0.1700
Data Index: 6347383 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0365. Min Range: -5.0365
Max Act: 4.6615. Min Act: -0.1700
Data Index: 5299193 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #19