Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 655 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9101. Min Range: -5.9101
Max Act: 5.9101. Min Act: -0.1700
Data Index: 5010494 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9101. Min Range: -5.9101
Max Act: 5.8788. Min Act: -0.1700
Data Index: 2775720 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9101. Min Range: -5.9101
Max Act: 5.8788. Min Act: -0.1700
Data Index: 3720244 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9101. Min Range: -5.9101
Max Act: 5.8163. Min Act: -0.1700
Data Index: 6646227 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9101. Min Range: -5.9101
Max Act: 5.7226. Min Act: -0.1700
Data Index: 2973084 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9101. Min Range: -5.9101
Max Act: 5.7538. Min Act: -0.1700
Data Index: 5477309 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9101. Min Range: -5.9101
Max Act: 5.6601. Min Act: -0.1700
Data Index: 757202 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9101. Min Range: -5.9101
Max Act: 5.7226. Min Act: -0.1700
Data Index: 6469367 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9101. Min Range: -5.9101
Max Act: 5.6913. Min Act: -0.1700
Data Index: 4157304 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9101. Min Range: -5.9101
Max Act: 5.6288. Min Act: -0.1700
Data Index: 8397322 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9101. Min Range: -5.9101
Max Act: 5.5663. Min Act: -0.1700
Data Index: 8458347 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9101. Min Range: -5.9101
Max Act: 5.5976. Min Act: -0.1700
Data Index: 6966259 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9101. Min Range: -5.9101
Max Act: 5.5663. Min Act: -0.1700
Data Index: 2823997 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9101. Min Range: -5.9101
Max Act: 5.5351. Min Act: -0.1700
Data Index: 1289517 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9101. Min Range: -5.9101
Max Act: 5.5663. Min Act: -0.1700
Data Index: 4568011 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9101. Min Range: -5.9101
Max Act: 5.5663. Min Act: -0.1700
Data Index: 7953499 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9101. Min Range: -5.9101
Max Act: 5.4413. Min Act: -0.1700
Data Index: 1176939 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9101. Min Range: -5.9101
Max Act: 5.4413. Min Act: -0.1700
Data Index: 7823607 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9101. Min Range: -5.9101
Max Act: 5.4101. Min Act: -0.1700
Data Index: 1473310 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9101. Min Range: -5.9101
Max Act: 5.4726. Min Act: -0.1700
Data Index: 3415679 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19