Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 254 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8913. Min Range: -6.8913
Max Act: 6.8913. Min Act: -0.1700
Data Index: 755361 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8913. Min Range: -6.8913
Max Act: 6.8288. Min Act: -0.1700
Data Index: 1330848 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8913. Min Range: -6.8913
Max Act: 6.7663. Min Act: -0.1700
Data Index: 4408696 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8913. Min Range: -6.8913
Max Act: 6.6725. Min Act: -0.1700
Data Index: 133390 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8913. Min Range: -6.8913
Max Act: 6.6413. Min Act: -0.1700
Data Index: 6372372 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8913. Min Range: -6.8913
Max Act: 6.6413. Min Act: -0.1700
Data Index: 6970835 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8913. Min Range: -6.8913
Max Act: 6.5788. Min Act: -0.1700
Data Index: 6640167 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8913. Min Range: -6.8913
Max Act: 6.5788. Min Act: -0.1700
Data Index: 5590388 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8913. Min Range: -6.8913
Max Act: 6.5788. Min Act: -0.1700
Data Index: 1663425 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8913. Min Range: -6.8913
Max Act: 6.5163. Min Act: -0.1700
Data Index: 4778961 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8913. Min Range: -6.8913
Max Act: 6.4850. Min Act: -0.1700
Data Index: 6666013 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8913. Min Range: -6.8913
Max Act: 6.4850. Min Act: -0.1700
Data Index: 2803887 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8913. Min Range: -6.8913
Max Act: 6.4538. Min Act: -0.1700
Data Index: 186245 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8913. Min Range: -6.8913
Max Act: 6.4225. Min Act: -0.1700
Data Index: 2789162 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8913. Min Range: -6.8913
Max Act: 6.4538. Min Act: -0.1700
Data Index: 3687618 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8913. Min Range: -6.8913
Max Act: 6.4538. Min Act: -0.1700
Data Index: 2989034 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8913. Min Range: -6.8913
Max Act: 6.4225. Min Act: -0.1700
Data Index: 7166372 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8913. Min Range: -6.8913
Max Act: 6.4225. Min Act: -0.1700
Data Index: 2890959 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8913. Min Range: -6.8913
Max Act: 6.3913. Min Act: -0.1700
Data Index: 1273022 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8913. Min Range: -6.8913
Max Act: 6.3600. Min Act: -0.1700
Data Index: 5578763 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19