Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3283 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1085. Min Range: -4.1085
Max Act: 4.1085. Min Act: -0.1700
Data Index: 1861859 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1085. Min Range: -4.1085
Max Act: 4.0460. Min Act: -0.1700
Data Index: 2283852 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1085. Min Range: -4.1085
Max Act: 4.0148. Min Act: -0.1700
Data Index: 1813156 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1085. Min Range: -4.1085
Max Act: 4.0148. Min Act: -0.1700
Data Index: 1716050 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1085. Min Range: -4.1085
Max Act: 3.9835. Min Act: -0.1700
Data Index: 5047292 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1085. Min Range: -4.1085
Max Act: 3.9522. Min Act: -0.1700
Data Index: 1343663 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1085. Min Range: -4.1085
Max Act: 3.9210. Min Act: -0.1700
Data Index: 8793127 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1085. Min Range: -4.1085
Max Act: 3.9522. Min Act: -0.1700
Data Index: 396636 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1085. Min Range: -4.1085
Max Act: 3.9210. Min Act: -0.1700
Data Index: 294331 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1085. Min Range: -4.1085
Max Act: 3.9522. Min Act: -0.1700
Data Index: 3437189 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1085. Min Range: -4.1085
Max Act: 3.9210. Min Act: -0.1700
Data Index: 8799127 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1085. Min Range: -4.1085
Max Act: 3.9210. Min Act: -0.1700
Data Index: 1785228 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1085. Min Range: -4.1085
Max Act: 3.9210. Min Act: -0.1700
Data Index: 1066184 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1085. Min Range: -4.1085
Max Act: 3.9210. Min Act: -0.1700
Data Index: 1308255 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1085. Min Range: -4.1085
Max Act: 3.8897. Min Act: -0.1700
Data Index: 1253196 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1085. Min Range: -4.1085
Max Act: 3.8897. Min Act: -0.1700
Data Index: 5684643 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1085. Min Range: -4.1085
Max Act: 3.8897. Min Act: -0.1700
Data Index: 7348560 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1085. Min Range: -4.1085
Max Act: 3.8897. Min Act: -0.1700
Data Index: 1942637 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1085. Min Range: -4.1085
Max Act: 3.8897. Min Act: -0.1700
Data Index: 29216 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1085. Min Range: -4.1085
Max Act: 3.8584. Min Act: -0.1700
Data Index: 1085869 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19