Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 33 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.7133. Min Act: -0.1700
Data Index: 6614262 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.6820. Min Act: -0.1700
Data Index: 6933727 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.5258. Min Act: -0.1700
Data Index: 963115 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.5570. Min Act: -0.1700
Data Index: 8125244 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.5570. Min Act: -0.1700
Data Index: 2115913 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.5570. Min Act: -0.1700
Data Index: 7439985 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.5258. Min Act: -0.1700
Data Index: 4722964 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.5258. Min Act: -0.1700
Data Index: 7201871 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.5258. Min Act: -0.1700
Data Index: 2529966 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4945. Min Act: -0.1700
Data Index: 2529962 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4633. Min Act: -0.1700
Data Index: 5921612 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4633. Min Act: -0.1700
Data Index: 7104668 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4320. Min Act: -0.1700
Data Index: 2417475 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4633. Min Act: -0.1700
Data Index: 1368206 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4320. Min Act: -0.1700
Data Index: 2529964 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4633. Min Act: -0.1700
Data Index: 6042366 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4320. Min Act: -0.1700
Data Index: 5815377 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4320. Min Act: -0.1700
Data Index: 2563163 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4320. Min Act: -0.1700
Data Index: 2504147 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7133. Min Range: -4.7133
Max Act: 4.4008. Min Act: -0.1700
Data Index: 4279958 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19