Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3733 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6361. Min Range: -2.6361
Max Act: 2.6361. Min Act: -0.1700
Data Index: 3400129 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6361. Min Range: -2.6361
Max Act: 2.6361. Min Act: -0.1700
Data Index: 418171 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6361. Min Range: -2.6361
Max Act: 2.6040. Min Act: -0.1700
Data Index: 7860497 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6361. Min Range: -2.6361
Max Act: 2.5395. Min Act: -0.1700
Data Index: 4502665 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6361. Min Range: -2.6361
Max Act: 2.5071. Min Act: -0.1700
Data Index: 7418379 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6361. Min Range: -2.6361
Max Act: 2.5233. Min Act: -0.1700
Data Index: 1543718 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6361. Min Range: -2.6361
Max Act: 2.5233. Min Act: -0.1700
Data Index: 787598 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6361. Min Range: -2.6361
Max Act: 2.4909. Min Act: -0.1700
Data Index: 983338 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6361. Min Range: -2.6361
Max Act: 2.4909. Min Act: -0.1700
Data Index: 8500114 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6361. Min Range: -2.6361
Max Act: 2.4909. Min Act: -0.1700
Data Index: 2798629 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6361. Min Range: -2.6361
Max Act: 2.4747. Min Act: -0.1700
Data Index: 7521429 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6361. Min Range: -2.6361
Max Act: 2.4585. Min Act: -0.1700
Data Index: 8755363 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6361. Min Range: -2.6361
Max Act: 2.4422. Min Act: -0.1700
Data Index: 5879039 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6361. Min Range: -2.6361
Max Act: 2.4259. Min Act: -0.1700
Data Index: 8696042 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6361. Min Range: -2.6361
Max Act: 2.4422. Min Act: -0.1700
Data Index: 2204217 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6361. Min Range: -2.6361
Max Act: 2.4422. Min Act: -0.1700
Data Index: 1518505 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6361. Min Range: -2.6361
Max Act: 2.4259. Min Act: -0.1700
Data Index: 8803330 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6361. Min Range: -2.6361
Max Act: 2.4422. Min Act: -0.1700
Data Index: 8633276 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6361. Min Range: -2.6361
Max Act: 2.4422. Min Act: -0.1700
Data Index: 8591727 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6361. Min Range: -2.6361
Max Act: 2.4259. Min Act: -0.1700
Data Index: 7526615 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19