Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2817 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7498. Min Range: -5.7498
Max Act: 5.7498. Min Act: -0.1700
Data Index: 2953863 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7498. Min Range: -5.7498
Max Act: 5.5935. Min Act: -0.1700
Data Index: 8008134 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7498. Min Range: -5.7498
Max Act: 5.4685. Min Act: -0.1700
Data Index: 5122686 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7498. Min Range: -5.7498
Max Act: 5.4060. Min Act: -0.1700
Data Index: 5936322 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7498. Min Range: -5.7498
Max Act: 5.3748. Min Act: -0.1700
Data Index: 151685 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7498. Min Range: -5.7498
Max Act: 5.3435. Min Act: -0.1700
Data Index: 3921247 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7498. Min Range: -5.7498
Max Act: 5.3123. Min Act: -0.1700
Data Index: 8297214 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7498. Min Range: -5.7498
Max Act: 5.3435. Min Act: -0.1700
Data Index: 4652832 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7498. Min Range: -5.7498
Max Act: 5.3123. Min Act: -0.1700
Data Index: 4454578 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7498. Min Range: -5.7498
Max Act: 5.2810. Min Act: -0.1700
Data Index: 4819682 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7498. Min Range: -5.7498
Max Act: 5.2498. Min Act: -0.1700
Data Index: 4491609 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7498. Min Range: -5.7498
Max Act: 5.2810. Min Act: -0.1700
Data Index: 7363257 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7498. Min Range: -5.7498
Max Act: 5.2498. Min Act: -0.1700
Data Index: 1034368 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7498. Min Range: -5.7498
Max Act: 5.2498. Min Act: -0.1700
Data Index: 1154330 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7498. Min Range: -5.7498
Max Act: 5.2498. Min Act: -0.1700
Data Index: 8559060 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7498. Min Range: -5.7498
Max Act: 5.2498. Min Act: -0.1700
Data Index: 3208926 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7498. Min Range: -5.7498
Max Act: 5.2498. Min Act: -0.1700
Data Index: 6121606 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7498. Min Range: -5.7498
Max Act: 5.2498. Min Act: -0.1700
Data Index: 2219353 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7498. Min Range: -5.7498
Max Act: 5.2498. Min Act: -0.1700
Data Index: 2428111 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7498. Min Range: -5.7498
Max Act: 5.2185. Min Act: -0.1700
Data Index: 2738043 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #19