Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2700 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1358. Min Range: -5.1358
Max Act: 5.1358. Min Act: -0.1700
Data Index: 1976702 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1358. Min Range: -5.1358
Max Act: 5.1045. Min Act: -0.1700
Data Index: 5412400 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1358. Min Range: -5.1358
Max Act: 5.0733. Min Act: -0.1700
Data Index: 1840470 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1358. Min Range: -5.1358
Max Act: 5.0733. Min Act: -0.1700
Data Index: 5155462 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1358. Min Range: -5.1358
Max Act: 5.1045. Min Act: -0.1700
Data Index: 8139199 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1358. Min Range: -5.1358
Max Act: 5.0108. Min Act: -0.1700
Data Index: 6602570 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1358. Min Range: -5.1358
Max Act: 5.0108. Min Act: -0.1700
Data Index: 5834969 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1358. Min Range: -5.1358
Max Act: 5.0108. Min Act: -0.1700
Data Index: 883839 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1358. Min Range: -5.1358
Max Act: 4.9795. Min Act: -0.1700
Data Index: 5242929 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1358. Min Range: -5.1358
Max Act: 4.9795. Min Act: -0.1700
Data Index: 4342972 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1358. Min Range: -5.1358
Max Act: 4.9483. Min Act: -0.1700
Data Index: 2375167 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1358. Min Range: -5.1358
Max Act: 4.9483. Min Act: -0.1700
Data Index: 724374 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1358. Min Range: -5.1358
Max Act: 4.9483. Min Act: -0.1700
Data Index: 6247001 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1358. Min Range: -5.1358
Max Act: 4.8858. Min Act: -0.1700
Data Index: 8572793 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1358. Min Range: -5.1358
Max Act: 4.9170. Min Act: -0.1700
Data Index: 4649970 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1358. Min Range: -5.1358
Max Act: 4.8545. Min Act: -0.1700
Data Index: 7826783 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1358. Min Range: -5.1358
Max Act: 4.8858. Min Act: -0.1700
Data Index: 430640 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1358. Min Range: -5.1358
Max Act: 4.8858. Min Act: -0.1700
Data Index: 8738458 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1358. Min Range: -5.1358
Max Act: 4.8858. Min Act: -0.1700
Data Index: 4294177 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1358. Min Range: -5.1358
Max Act: 4.8545. Min Act: -0.1700
Data Index: 338036 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19