Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 136 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6615. Min Range: -5.6615
Max Act: 5.6615. Min Act: -0.1700
Data Index: 6515430 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6615. Min Range: -5.6615
Max Act: 5.5677. Min Act: -0.1700
Data Index: 6900960 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6615. Min Range: -5.6615
Max Act: 5.5365. Min Act: -0.1700
Data Index: 7412178 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6615. Min Range: -5.6615
Max Act: 5.3802. Min Act: -0.1700
Data Index: 994885 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6615. Min Range: -5.6615
Max Act: 5.2552. Min Act: -0.1700
Data Index: 3648100 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6615. Min Range: -5.6615
Max Act: 5.2552. Min Act: -0.1700
Data Index: 1072432 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6615. Min Range: -5.6615
Max Act: 5.2240. Min Act: -0.1700
Data Index: 4829859 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6615. Min Range: -5.6615
Max Act: 5.2240. Min Act: -0.1700
Data Index: 6278441 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6615. Min Range: -5.6615
Max Act: 5.1927. Min Act: -0.1700
Data Index: 8433634 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6615. Min Range: -5.6615
Max Act: 5.2240. Min Act: -0.1700
Data Index: 8170834 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6615. Min Range: -5.6615
Max Act: 5.1615. Min Act: -0.1700
Data Index: 7162220 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6615. Min Range: -5.6615
Max Act: 5.1615. Min Act: -0.1700
Data Index: 4217859 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6615. Min Range: -5.6615
Max Act: 5.1615. Min Act: -0.1700
Data Index: 7733807 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6615. Min Range: -5.6615
Max Act: 5.1615. Min Act: -0.1700
Data Index: 4368032 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6615. Min Range: -5.6615
Max Act: 5.1302. Min Act: -0.1700
Data Index: 6393409 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6615. Min Range: -5.6615
Max Act: 5.0990. Min Act: -0.1700
Data Index: 7970118 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6615. Min Range: -5.6615
Max Act: 5.0990. Min Act: -0.1700
Data Index: 6434377 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6615. Min Range: -5.6615
Max Act: 5.0990. Min Act: -0.1700
Data Index: 1148395 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6615. Min Range: -5.6615
Max Act: 5.0990. Min Act: -0.1700
Data Index: 3993570 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6615. Min Range: -5.6615
Max Act: 5.0990. Min Act: -0.1700
Data Index: 2873340 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #19