Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3069 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5139. Min Range: -3.5139
Max Act: 3.5139. Min Act: -0.1700
Data Index: 4907280 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5139. Min Range: -3.5139
Max Act: 3.3886. Min Act: -0.1700
Data Index: 6128220 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5139. Min Range: -3.5139
Max Act: 3.3101. Min Act: -0.1700
Data Index: 2552575 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5139. Min Range: -3.5139
Max Act: 3.2944. Min Act: -0.1700
Data Index: 7295046 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5139. Min Range: -3.5139
Max Act: 3.3258. Min Act: -0.1700
Data Index: 1154025 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5139. Min Range: -3.5139
Max Act: 3.3101. Min Act: -0.1700
Data Index: 5521404 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5139. Min Range: -3.5139
Max Act: 3.2787. Min Act: -0.1700
Data Index: 4035453 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5139. Min Range: -3.5139
Max Act: 3.2787. Min Act: -0.1700
Data Index: 256817 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5139. Min Range: -3.5139
Max Act: 3.2944. Min Act: -0.1700
Data Index: 3795136 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5139. Min Range: -3.5139
Max Act: 3.2630. Min Act: -0.1700
Data Index: 6128173 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5139. Min Range: -3.5139
Max Act: 3.2473. Min Act: -0.1700
Data Index: 5581262 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5139. Min Range: -3.5139
Max Act: 3.2159. Min Act: -0.1700
Data Index: 4583821 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5139. Min Range: -3.5139
Max Act: 3.2316. Min Act: -0.1700
Data Index: 2098037 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5139. Min Range: -3.5139
Max Act: 3.2159. Min Act: -0.1700
Data Index: 1182227 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5139. Min Range: -3.5139
Max Act: 3.2316. Min Act: -0.1700
Data Index: 2116309 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5139. Min Range: -3.5139
Max Act: 3.2001. Min Act: -0.1700
Data Index: 3164223 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5139. Min Range: -3.5139
Max Act: 3.1687. Min Act: -0.1700
Data Index: 7265030 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5139. Min Range: -3.5139
Max Act: 3.1844. Min Act: -0.1700
Data Index: 1310295 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5139. Min Range: -3.5139
Max Act: 3.1844. Min Act: -0.1700
Data Index: 3066648 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5139. Min Range: -3.5139
Max Act: 3.2001. Min Act: -0.1700
Data Index: 3631461 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19