Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2735 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.9307. Min Act: -0.1700
Data Index: 2506775 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.9307. Min Act: -0.1700
Data Index: 5726186 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.8831. Min Act: -0.1700
Data Index: 5908222 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.8672. Min Act: -0.1700
Data Index: 2001000 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.8355. Min Act: -0.1700
Data Index: 1935376 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.8195. Min Act: -0.1700
Data Index: 1869915 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.8036. Min Act: -0.1700
Data Index: 2165255 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.7718. Min Act: -0.1700
Data Index: 2777116 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.7877. Min Act: -0.1700
Data Index: 8052982 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.7718. Min Act: -0.1700
Data Index: 2175 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.7558. Min Act: -0.1700
Data Index: 521735 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.7558. Min Act: -0.1700
Data Index: 6866858 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.7718. Min Act: -0.1700
Data Index: 5710111 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.7399. Min Act: -0.1700
Data Index: 6156977 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.7399. Min Act: -0.1700
Data Index: 1599467 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.7399. Min Act: -0.1700
Data Index: 4279610 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.7399. Min Act: -0.1700
Data Index: 3703465 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.7239. Min Act: -0.1700
Data Index: 5915982 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.7239. Min Act: -0.1700
Data Index: 4846178 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9307. Min Range: -2.9307
Max Act: 2.7079. Min Act: -0.1700
Data Index: 3407008 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19