Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2783 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3427. Min Range: -4.3427
Max Act: 4.3114. Min Act: -0.1700
Data Index: 1451217 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3427. Min Range: -4.3427
Max Act: 4.3427. Min Act: -0.1700
Data Index: 438125 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3427. Min Range: -4.3427
Max Act: 4.2801. Min Act: -0.1700
Data Index: 170532 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3427. Min Range: -4.3427
Max Act: 4.2489. Min Act: -0.1700
Data Index: 1507267 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3427. Min Range: -4.3427
Max Act: 4.2489. Min Act: -0.1700
Data Index: 3253091 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3427. Min Range: -4.3427
Max Act: 4.2176. Min Act: -0.1700
Data Index: 5065735 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3427. Min Range: -4.3427
Max Act: 4.2176. Min Act: -0.1700
Data Index: 1109240 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3427. Min Range: -4.3427
Max Act: 4.2176. Min Act: -0.1700
Data Index: 6496017 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3427. Min Range: -4.3427
Max Act: 4.2176. Min Act: -0.1700
Data Index: 6982933 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3427. Min Range: -4.3427
Max Act: 4.1864. Min Act: -0.1700
Data Index: 2535832 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3427. Min Range: -4.3427
Max Act: 4.2176. Min Act: -0.1700
Data Index: 1359976 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3427. Min Range: -4.3427
Max Act: 4.2176. Min Act: -0.1700
Data Index: 5008338 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3427. Min Range: -4.3427
Max Act: 4.2176. Min Act: -0.1700
Data Index: 8428924 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3427. Min Range: -4.3427
Max Act: 4.1864. Min Act: -0.1700
Data Index: 738562 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3427. Min Range: -4.3427
Max Act: 4.2176. Min Act: -0.1700
Data Index: 8775080 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3427. Min Range: -4.3427
Max Act: 4.2176. Min Act: -0.1700
Data Index: 4500744 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3427. Min Range: -4.3427
Max Act: 4.1864. Min Act: -0.1700
Data Index: 4425812 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3427. Min Range: -4.3427
Max Act: 4.2176. Min Act: -0.1700
Data Index: 1681634 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3427. Min Range: -4.3427
Max Act: 4.1864. Min Act: -0.1700
Data Index: 3286954 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3427. Min Range: -4.3427
Max Act: 4.1864. Min Act: -0.1700
Data Index: 3925546 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19