Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 3069 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.8109. Min Act: -0.1700
Data Index: 7719246 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.7831. Min Act: -0.1700
Data Index: 2240179 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.6847. Min Act: -0.1700
Data Index: 5584510 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.7065. Min Act: -0.1700
Data Index: 8503580 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.7180. Min Act: -0.1700
Data Index: 6079394 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.6970. Min Act: -0.1700
Data Index: 4526531 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.6777. Min Act: -0.1700
Data Index: 5002742 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.6672. Min Act: -0.1700
Data Index: 5137781 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.6303. Min Act: -0.1700
Data Index: 4053439 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.6443. Min Act: -0.1700
Data Index: 1272857 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.6212. Min Act: -0.1700
Data Index: 6738172 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.6040. Min Act: -0.1700
Data Index: 6374366 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.5891. Min Act: -0.1700
Data Index: 8487270 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.5952. Min Act: -0.1700
Data Index: 8582417 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.5825. Min Act: -0.1700
Data Index: 2547006 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.5833. Min Act: -0.1700
Data Index: 3984162 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.5726. Min Act: -0.1700
Data Index: 7484979 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.5641. Min Act: -0.1700
Data Index: 6364467 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.5832. Min Act: -0.1700
Data Index: 5052563 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.5635. Min Act: -0.1700
Data Index: 2932701 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full textTruncated
Full Text #19