Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2712 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6413. Min Range: -4.6413
Max Act: 4.6413. Min Act: -0.1700
Data Index: 515812 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6413. Min Range: -4.6413
Max Act: 4.6100. Min Act: -0.1700
Data Index: 4717268 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6413. Min Range: -4.6413
Max Act: 4.5788. Min Act: -0.1700
Data Index: 7932693 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6413. Min Range: -4.6413
Max Act: 4.4850. Min Act: -0.1700
Data Index: 5233693 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6413. Min Range: -4.6413
Max Act: 4.3913. Min Act: -0.1700
Data Index: 7928360 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6413. Min Range: -4.6413
Max Act: 4.3600. Min Act: -0.1700
Data Index: 2206472 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6413. Min Range: -4.6413
Max Act: 4.3913. Min Act: -0.1700
Data Index: 406283 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6413. Min Range: -4.6413
Max Act: 4.3913. Min Act: -0.1700
Data Index: 2263143 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6413. Min Range: -4.6413
Max Act: 4.3288. Min Act: -0.1700
Data Index: 6752655 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6413. Min Range: -4.6413
Max Act: 4.3288. Min Act: -0.1700
Data Index: 406284 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6413. Min Range: -4.6413
Max Act: 4.3288. Min Act: -0.1700
Data Index: 7845362 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6413. Min Range: -4.6413
Max Act: 4.2663. Min Act: -0.1700
Data Index: 6162049 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6413. Min Range: -4.6413
Max Act: 4.2975. Min Act: -0.1700
Data Index: 406280 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6413. Min Range: -4.6413
Max Act: 4.2350. Min Act: -0.1700
Data Index: 8351909 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6413. Min Range: -4.6413
Max Act: 4.2663. Min Act: -0.1700
Data Index: 5177360 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6413. Min Range: -4.6413
Max Act: 4.2350. Min Act: -0.1700
Data Index: 4860934 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6413. Min Range: -4.6413
Max Act: 4.2663. Min Act: -0.1700
Data Index: 5191681 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6413. Min Range: -4.6413
Max Act: 4.2038. Min Act: -0.1700
Data Index: 3976731 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6413. Min Range: -4.6413
Max Act: 4.2038. Min Act: -0.1700
Data Index: 406278 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6413. Min Range: -4.6413
Max Act: 4.2038. Min Act: -0.1700
Data Index: 1841478 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19