Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4615 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5010. Min Range: -5.5010
Max Act: 5.5010. Min Act: -0.1700
Data Index: 1736204 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5010. Min Range: -5.5010
Max Act: 5.4073. Min Act: -0.1700
Data Index: 7763792 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5010. Min Range: -5.5010
Max Act: 5.3760. Min Act: -0.1700
Data Index: 7843241 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5010. Min Range: -5.5010
Max Act: 5.3448. Min Act: -0.1700
Data Index: 4277212 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5010. Min Range: -5.5010
Max Act: 5.3448. Min Act: -0.1700
Data Index: 3538079 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5010. Min Range: -5.5010
Max Act: 5.3135. Min Act: -0.1700
Data Index: 3834315 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5010. Min Range: -5.5010
Max Act: 5.2510. Min Act: -0.1700
Data Index: 4756788 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5010. Min Range: -5.5010
Max Act: 5.2510. Min Act: -0.1700
Data Index: 1172056 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5010. Min Range: -5.5010
Max Act: 5.2510. Min Act: -0.1700
Data Index: 8613431 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5010. Min Range: -5.5010
Max Act: 5.2198. Min Act: -0.1700
Data Index: 4648606 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5010. Min Range: -5.5010
Max Act: 5.2198. Min Act: -0.1700
Data Index: 460648 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5010. Min Range: -5.5010
Max Act: 5.2198. Min Act: -0.1700
Data Index: 4648605 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5010. Min Range: -5.5010
Max Act: 5.2198. Min Act: -0.1700
Data Index: 7960016 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5010. Min Range: -5.5010
Max Act: 5.2198. Min Act: -0.1700
Data Index: 3017812 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5010. Min Range: -5.5010
Max Act: 5.1573. Min Act: -0.1700
Data Index: 4542896 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5010. Min Range: -5.5010
Max Act: 5.1573. Min Act: -0.1700
Data Index: 7977056 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5010. Min Range: -5.5010
Max Act: 5.1260. Min Act: -0.1700
Data Index: 7143862 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5010. Min Range: -5.5010
Max Act: 5.1260. Min Act: -0.1700
Data Index: 2883283 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5010. Min Range: -5.5010
Max Act: 5.1573. Min Act: -0.1700
Data Index: 7109645 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5010. Min Range: -5.5010
Max Act: 5.1260. Min Act: -0.1700
Data Index: 2361261 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19