Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6022 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2241. Min Range: -6.2241
Max Act: 6.2241. Min Act: -0.1700
Data Index: 8513063 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2241. Min Range: -6.2241
Max Act: 6.1303. Min Act: -0.1700
Data Index: 3300943 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2241. Min Range: -6.2241
Max Act: 6.0991. Min Act: -0.1700
Data Index: 3300944 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2241. Min Range: -6.2241
Max Act: 6.0678. Min Act: -0.1700
Data Index: 6522994 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2241. Min Range: -6.2241
Max Act: 6.0366. Min Act: -0.1700
Data Index: 4169507 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2241. Min Range: -6.2241
Max Act: 5.8491. Min Act: -0.1700
Data Index: 3855413 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2241. Min Range: -6.2241
Max Act: 5.8178. Min Act: -0.1700
Data Index: 692637 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2241. Min Range: -6.2241
Max Act: 5.7866. Min Act: -0.1700
Data Index: 2955074 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2241. Min Range: -6.2241
Max Act: 5.7866. Min Act: -0.1700
Data Index: 6068962 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2241. Min Range: -6.2241
Max Act: 5.7553. Min Act: -0.1700
Data Index: 7978495 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2241. Min Range: -6.2241
Max Act: 5.7553. Min Act: -0.1700
Data Index: 8751099 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2241. Min Range: -6.2241
Max Act: 5.7241. Min Act: -0.1700
Data Index: 8302451 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2241. Min Range: -6.2241
Max Act: 5.6928. Min Act: -0.1700
Data Index: 5075643 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2241. Min Range: -6.2241
Max Act: 5.6928. Min Act: -0.1700
Data Index: 1960604 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2241. Min Range: -6.2241
Max Act: 5.6616. Min Act: -0.1700
Data Index: 3924343 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2241. Min Range: -6.2241
Max Act: 5.6616. Min Act: -0.1700
Data Index: 5381342 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2241. Min Range: -6.2241
Max Act: 5.6616. Min Act: -0.1700
Data Index: 7207503 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2241. Min Range: -6.2241
Max Act: 5.5991. Min Act: -0.1700
Data Index: 1006409 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2241. Min Range: -6.2241
Max Act: 5.5991. Min Act: -0.1700
Data Index: 899830 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2241. Min Range: -6.2241
Max Act: 5.5991. Min Act: -0.1700
Data Index: 4799735 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19