Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 772 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4970. Min Range: -4.4970
Max Act: 4.4970. Min Act: -0.1700
Data Index: 5256026 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4970. Min Range: -4.4970
Max Act: 4.4970. Min Act: -0.1700
Data Index: 7189576 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4970. Min Range: -4.4970
Max Act: 4.4970. Min Act: -0.1700
Data Index: 812467 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4970. Min Range: -4.4970
Max Act: 4.4970. Min Act: -0.1700
Data Index: 623853 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4970. Min Range: -4.4970
Max Act: 4.4970. Min Act: -0.1700
Data Index: 7039190 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4970. Min Range: -4.4970
Max Act: 4.4970. Min Act: -0.1700
Data Index: 7915780 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4970. Min Range: -4.4970
Max Act: 4.4970. Min Act: -0.1700
Data Index: 1904554 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4970. Min Range: -4.4970
Max Act: 4.4970. Min Act: -0.1700
Data Index: 670436 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4970. Min Range: -4.4970
Max Act: 4.4970. Min Act: -0.1700
Data Index: 845284 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4970. Min Range: -4.4970
Max Act: 4.4970. Min Act: -0.1700
Data Index: 6772345 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4970. Min Range: -4.4970
Max Act: 4.4970. Min Act: -0.1700
Data Index: 2863556 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4970. Min Range: -4.4970
Max Act: 4.4970. Min Act: -0.1700
Data Index: 6549810 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4970. Min Range: -4.4970
Max Act: 4.4970. Min Act: -0.1700
Data Index: 4726084 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4970. Min Range: -4.4970
Max Act: 4.4970. Min Act: -0.1700
Data Index: 4042484 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4970. Min Range: -4.4970
Max Act: 4.4657. Min Act: -0.1700
Data Index: 2874335 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4970. Min Range: -4.4970
Max Act: 4.4345. Min Act: -0.1700
Data Index: 5947910 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4970. Min Range: -4.4970
Max Act: 4.4345. Min Act: -0.1700
Data Index: 1002289 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4970. Min Range: -4.4970
Max Act: 4.4032. Min Act: -0.1700
Data Index: 7436246 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4970. Min Range: -4.4970
Max Act: 4.3720. Min Act: -0.1700
Data Index: 5933499 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4970. Min Range: -4.4970
Max Act: 4.4032. Min Act: -0.1700
Data Index: 3734298 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19