Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5093 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.7135. Min Range: -7.7135
Max Act: 7.7135. Min Act: -0.1700
Data Index: 8274070 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7135. Min Range: -7.7135
Max Act: 7.6197. Min Act: -0.1700
Data Index: 5128705 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7135. Min Range: -7.7135
Max Act: 7.5885. Min Act: -0.1700
Data Index: 7739938 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7135. Min Range: -7.7135
Max Act: 7.4322. Min Act: -0.1700
Data Index: 3993203 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7135. Min Range: -7.7135
Max Act: 7.4010. Min Act: -0.1700
Data Index: 1467862 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7135. Min Range: -7.7135
Max Act: 7.4322. Min Act: -0.1700
Data Index: 2521831 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7135. Min Range: -7.7135
Max Act: 7.2760. Min Act: -0.1700
Data Index: 5340284 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7135. Min Range: -7.7135
Max Act: 7.3072. Min Act: -0.1700
Data Index: 5253680 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7135. Min Range: -7.7135
Max Act: 7.3072. Min Act: -0.1700
Data Index: 4919225 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7135. Min Range: -7.7135
Max Act: 7.2760. Min Act: -0.1700
Data Index: 5504985 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7135. Min Range: -7.7135
Max Act: 7.2760. Min Act: -0.1700
Data Index: 6277639 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7135. Min Range: -7.7135
Max Act: 7.2447. Min Act: -0.1700
Data Index: 2534390 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7135. Min Range: -7.7135
Max Act: 7.2135. Min Act: -0.1700
Data Index: 4142836 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7135. Min Range: -7.7135
Max Act: 7.2135. Min Act: -0.1700
Data Index: 8529501 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7135. Min Range: -7.7135
Max Act: 7.2135. Min Act: -0.1700
Data Index: 6982918 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7135. Min Range: -7.7135
Max Act: 7.2135. Min Act: -0.1700
Data Index: 7585266 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7135. Min Range: -7.7135
Max Act: 7.2135. Min Act: -0.1700
Data Index: 536482 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7135. Min Range: -7.7135
Max Act: 7.2135. Min Act: -0.1700
Data Index: 8170235 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7135. Min Range: -7.7135
Max Act: 7.1510. Min Act: -0.1700
Data Index: 311107 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7135. Min Range: -7.7135
Max Act: 7.1510. Min Act: -0.1700
Data Index: 3355450 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19