Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3370 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9970. Min Range: -5.9970
Max Act: 5.9970. Min Act: -0.1700
Data Index: 1927765 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9970. Min Range: -5.9970
Max Act: 5.7158. Min Act: -0.1700
Data Index: 1155100 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9970. Min Range: -5.9970
Max Act: 5.5595. Min Act: -0.1700
Data Index: 7875058 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9970. Min Range: -5.9970
Max Act: 5.4970. Min Act: -0.1700
Data Index: 4707885 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9970. Min Range: -5.9970
Max Act: 5.4970. Min Act: -0.1700
Data Index: 8695146 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9970. Min Range: -5.9970
Max Act: 5.4970. Min Act: -0.1700
Data Index: 3365678 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9970. Min Range: -5.9970
Max Act: 5.4345. Min Act: -0.1700
Data Index: 8473473 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9970. Min Range: -5.9970
Max Act: 5.4345. Min Act: -0.1700
Data Index: 3660011 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9970. Min Range: -5.9970
Max Act: 5.4033. Min Act: -0.1700
Data Index: 2162492 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9970. Min Range: -5.9970
Max Act: 5.3408. Min Act: -0.1700
Data Index: 8583006 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9970. Min Range: -5.9970
Max Act: 5.3408. Min Act: -0.1700
Data Index: 6034482 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9970. Min Range: -5.9970
Max Act: 5.3408. Min Act: -0.1700
Data Index: 8012069 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9970. Min Range: -5.9970
Max Act: 5.3095. Min Act: -0.1700
Data Index: 5623602 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9970. Min Range: -5.9970
Max Act: 5.3095. Min Act: -0.1700
Data Index: 8241554 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9970. Min Range: -5.9970
Max Act: 5.3095. Min Act: -0.1700
Data Index: 4730485 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9970. Min Range: -5.9970
Max Act: 5.2783. Min Act: -0.1700
Data Index: 3802250 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9970. Min Range: -5.9970
Max Act: 5.2783. Min Act: -0.1700
Data Index: 4520814 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9970. Min Range: -5.9970
Max Act: 5.2783. Min Act: -0.1700
Data Index: 268920 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9970. Min Range: -5.9970
Max Act: 5.2783. Min Act: -0.1700
Data Index: 8115452 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9970. Min Range: -5.9970
Max Act: 5.2470. Min Act: -0.1700
Data Index: 2950673 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19