Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 244 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9735. Min Range: -6.9735
Max Act: 6.9735. Min Act: -0.1700
Data Index: 5821237 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9735. Min Range: -6.9735
Max Act: 6.5985. Min Act: -0.1700
Data Index: 6828761 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9735. Min Range: -6.9735
Max Act: 6.5047. Min Act: -0.1700
Data Index: 680825 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9735. Min Range: -6.9735
Max Act: 6.4735. Min Act: -0.1700
Data Index: 7924417 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9735. Min Range: -6.9735
Max Act: 6.4422. Min Act: -0.1700
Data Index: 1713902 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9735. Min Range: -6.9735
Max Act: 6.3797. Min Act: -0.1700
Data Index: 1027930 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9735. Min Range: -6.9735
Max Act: 6.3797. Min Act: -0.1700
Data Index: 4902062 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9735. Min Range: -6.9735
Max Act: 6.3485. Min Act: -0.1700
Data Index: 3614435 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9735. Min Range: -6.9735
Max Act: 6.3172. Min Act: -0.1700
Data Index: 229727 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9735. Min Range: -6.9735
Max Act: 6.3172. Min Act: -0.1700
Data Index: 6265436 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9735. Min Range: -6.9735
Max Act: 6.2860. Min Act: -0.1700
Data Index: 3688304 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9735. Min Range: -6.9735
Max Act: 6.2547. Min Act: -0.1700
Data Index: 5589361 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9735. Min Range: -6.9735
Max Act: 6.2547. Min Act: -0.1700
Data Index: 3129285 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9735. Min Range: -6.9735
Max Act: 6.2547. Min Act: -0.1700
Data Index: 618970 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9735. Min Range: -6.9735
Max Act: 6.2547. Min Act: -0.1700
Data Index: 112902 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9735. Min Range: -6.9735
Max Act: 6.2235. Min Act: -0.1700
Data Index: 5338878 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9735. Min Range: -6.9735
Max Act: 6.1610. Min Act: -0.1700
Data Index: 2422922 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9735. Min Range: -6.9735
Max Act: 6.1610. Min Act: -0.1700
Data Index: 4358809 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9735. Min Range: -6.9735
Max Act: 6.1297. Min Act: -0.1700
Data Index: 7919245 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9735. Min Range: -6.9735
Max Act: 6.1610. Min Act: -0.1700
Data Index: 4945623 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #19