Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3357 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.7927. Min Act: -0.1700
Data Index: 2852716 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.8240. Min Act: -0.1700
Data Index: 3697831 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.8552. Min Act: -0.1700
Data Index: 2074283 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.7927. Min Act: -0.1700
Data Index: 2164047 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.7927. Min Act: -0.1700
Data Index: 904961 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.7615. Min Act: -0.1700
Data Index: 288731 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.7615. Min Act: -0.1700
Data Index: 904954 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.7302. Min Act: -0.1700
Data Index: 1073484 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.7302. Min Act: -0.1700
Data Index: 6030828 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.6990. Min Act: -0.1700
Data Index: 3058589 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.6990. Min Act: -0.1700
Data Index: 2084159 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.7302. Min Act: -0.1700
Data Index: 1826172 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.6990. Min Act: -0.1700
Data Index: 904960 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.6990. Min Act: -0.1700
Data Index: 4390725 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.6677. Min Act: -0.1700
Data Index: 2582656 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.6990. Min Act: -0.1700
Data Index: 2389965 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.6677. Min Act: -0.1700
Data Index: 2250265 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.6677. Min Act: -0.1700
Data Index: 2490711 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.6990. Min Act: -0.1700
Data Index: 308198 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8552. Min Range: -4.8552
Max Act: 4.6365. Min Act: -0.1700
Data Index: 2490710 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #19