Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3993 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9463. Min Range: -6.9463
Max Act: 6.9463. Min Act: -0.1700
Data Index: 2028985 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9463. Min Range: -6.9463
Max Act: 6.7588. Min Act: -0.1700
Data Index: 3197113 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9463. Min Range: -6.9463
Max Act: 6.7276. Min Act: -0.1700
Data Index: 2445057 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9463. Min Range: -6.9463
Max Act: 6.7276. Min Act: -0.1700
Data Index: 6685266 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9463. Min Range: -6.9463
Max Act: 6.6651. Min Act: -0.1700
Data Index: 5966296 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9463. Min Range: -6.9463
Max Act: 6.6651. Min Act: -0.1700
Data Index: 4193159 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9463. Min Range: -6.9463
Max Act: 6.6338. Min Act: -0.1700
Data Index: 2204968 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9463. Min Range: -6.9463
Max Act: 6.6651. Min Act: -0.1700
Data Index: 1510643 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9463. Min Range: -6.9463
Max Act: 6.6026. Min Act: -0.1700
Data Index: 8180631 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9463. Min Range: -6.9463
Max Act: 6.6338. Min Act: -0.1700
Data Index: 627595 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9463. Min Range: -6.9463
Max Act: 6.6026. Min Act: -0.1700
Data Index: 2004682 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9463. Min Range: -6.9463
Max Act: 6.6026. Min Act: -0.1700
Data Index: 7964027 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9463. Min Range: -6.9463
Max Act: 6.6338. Min Act: -0.1700
Data Index: 3641150 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9463. Min Range: -6.9463
Max Act: 6.6026. Min Act: -0.1700
Data Index: 6641320 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9463. Min Range: -6.9463
Max Act: 6.5401. Min Act: -0.1700
Data Index: 2306155 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9463. Min Range: -6.9463
Max Act: 6.5713. Min Act: -0.1700
Data Index: 6086253 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9463. Min Range: -6.9463
Max Act: 6.5713. Min Act: -0.1700
Data Index: 686918 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9463. Min Range: -6.9463
Max Act: 6.5713. Min Act: -0.1700
Data Index: 3120233 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9463. Min Range: -6.9463
Max Act: 6.5713. Min Act: -0.1700
Data Index: 5650344 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9463. Min Range: -6.9463
Max Act: 6.6026. Min Act: -0.1700
Data Index: 6305539 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19