Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5396 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3275. Min Range: -3.3275
Max Act: 3.3275. Min Act: -0.1653
Data Index: 914538 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3275. Min Range: -3.3275
Max Act: 3.1704. Min Act: -0.1700
Data Index: 7394732 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3275. Min Range: -3.3275
Max Act: 3.1074. Min Act: -0.1700
Data Index: 1869244 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3275. Min Range: -3.3275
Max Act: 3.0443. Min Act: -0.1700
Data Index: 4861183 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3275. Min Range: -3.3275
Max Act: 3.0443. Min Act: -0.1699
Data Index: 7146379 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3275. Min Range: -3.3275
Max Act: 3.0127. Min Act: -0.1700
Data Index: 1610111 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3275. Min Range: -3.3275
Max Act: 3.0127. Min Act: -0.1697
Data Index: 6237435 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3275. Min Range: -3.3275
Max Act: 2.9495. Min Act: -0.1700
Data Index: 538219 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3275. Min Range: -3.3275
Max Act: 2.9178. Min Act: -0.1700
Data Index: 8131017 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3275. Min Range: -3.3275
Max Act: 2.9178. Min Act: -0.1699
Data Index: 7067500 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3275. Min Range: -3.3275
Max Act: 2.9178. Min Act: -0.1700
Data Index: 8469871 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3275. Min Range: -3.3275
Max Act: 2.9178. Min Act: -0.1700
Data Index: 2883329 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3275. Min Range: -3.3275
Max Act: 2.8543. Min Act: -0.1696
Data Index: 3335645 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3275. Min Range: -3.3275
Max Act: 2.8543. Min Act: -0.1700
Data Index: 3931828 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3275. Min Range: -3.3275
Max Act: 2.8861. Min Act: -0.1700
Data Index: 2005481 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3275. Min Range: -3.3275
Max Act: 2.8225. Min Act: -0.1699
Data Index: 3631990 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3275. Min Range: -3.3275
Max Act: 2.7907. Min Act: -0.1699
Data Index: 417751 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3275. Min Range: -3.3275
Max Act: 2.8066. Min Act: -0.1696
Data Index: 1932769 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3275. Min Range: -3.3275
Max Act: 2.8066. Min Act: -0.1700
Data Index: 6900583 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3275. Min Range: -3.3275
Max Act: 2.7907. Min Act: -0.1594
Data Index: 3449039 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19