Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1909 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.8854. Min Range: -8.8854
Max Act: 8.8854. Min Act: -0.1700
Data Index: 1016958 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8854. Min Range: -8.8854
Max Act: 8.3229. Min Act: -0.1700
Data Index: 2047433 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8854. Min Range: -8.8854
Max Act: 8.3229. Min Act: -0.1700
Data Index: 7130676 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8854. Min Range: -8.8854
Max Act: 8.1354. Min Act: -0.1700
Data Index: 6355097 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8854. Min Range: -8.8854
Max Act: 8.0104. Min Act: -0.1700
Data Index: 7497759 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8854. Min Range: -8.8854
Max Act: 7.9479. Min Act: -0.1700
Data Index: 7923142 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8854. Min Range: -8.8854
Max Act: 7.9479. Min Act: -0.1700
Data Index: 6058926 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8854. Min Range: -8.8854
Max Act: 7.9479. Min Act: -0.1700
Data Index: 8165389 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8854. Min Range: -8.8854
Max Act: 7.8854. Min Act: -0.1700
Data Index: 3172921 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8854. Min Range: -8.8854
Max Act: 7.8854. Min Act: -0.1700
Data Index: 742317 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8854. Min Range: -8.8854
Max Act: 7.8541. Min Act: -0.1700
Data Index: 4458799 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8854. Min Range: -8.8854
Max Act: 7.8541. Min Act: -0.1700
Data Index: 4928836 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8854. Min Range: -8.8854
Max Act: 7.8229. Min Act: -0.1700
Data Index: 8076487 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8854. Min Range: -8.8854
Max Act: 7.8229. Min Act: -0.1700
Data Index: 1982482 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8854. Min Range: -8.8854
Max Act: 7.8229. Min Act: -0.1700
Data Index: 1117801 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8854. Min Range: -8.8854
Max Act: 7.7916. Min Act: -0.1700
Data Index: 8130389 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8854. Min Range: -8.8854
Max Act: 7.7916. Min Act: -0.1700
Data Index: 8237351 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8854. Min Range: -8.8854
Max Act: 7.7916. Min Act: -0.1700
Data Index: 1082002 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8854. Min Range: -8.8854
Max Act: 7.7604. Min Act: -0.1700
Data Index: 634435 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8854. Min Range: -8.8854
Max Act: 7.7604. Min Act: -0.1700
Data Index: 6730655 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #19