Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4463 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2352. Min Range: -5.2352
Max Act: 5.2352. Min Act: -0.1700
Data Index: 7866557 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2352. Min Range: -5.2352
Max Act: 5.2040. Min Act: -0.1700
Data Index: 8573752 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2352. Min Range: -5.2352
Max Act: 5.1727. Min Act: -0.1700
Data Index: 8130543 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2352. Min Range: -5.2352
Max Act: 5.1102. Min Act: -0.1700
Data Index: 2165667 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2352. Min Range: -5.2352
Max Act: 5.1415. Min Act: -0.1700
Data Index: 5344970 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2352. Min Range: -5.2352
Max Act: 5.0790. Min Act: -0.1700
Data Index: 8160140 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2352. Min Range: -5.2352
Max Act: 5.0790. Min Act: -0.1700
Data Index: 1566467 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2352. Min Range: -5.2352
Max Act: 5.0477. Min Act: -0.1700
Data Index: 6994692 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2352. Min Range: -5.2352
Max Act: 5.0165. Min Act: -0.1700
Data Index: 1047603 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2352. Min Range: -5.2352
Max Act: 4.9852. Min Act: -0.1700
Data Index: 2429268 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2352. Min Range: -5.2352
Max Act: 4.9852. Min Act: -0.1700
Data Index: 5881423 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2352. Min Range: -5.2352
Max Act: 5.0165. Min Act: -0.1700
Data Index: 5695705 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2352. Min Range: -5.2352
Max Act: 4.9540. Min Act: -0.1700
Data Index: 2225708 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2352. Min Range: -5.2352
Max Act: 4.9540. Min Act: -0.1700
Data Index: 6293034 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2352. Min Range: -5.2352
Max Act: 4.9540. Min Act: -0.1700
Data Index: 2447994 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2352. Min Range: -5.2352
Max Act: 4.9540. Min Act: -0.1700
Data Index: 4842810 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2352. Min Range: -5.2352
Max Act: 4.9227. Min Act: -0.1700
Data Index: 1109912 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2352. Min Range: -5.2352
Max Act: 4.9227. Min Act: -0.1700
Data Index: 6857865 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2352. Min Range: -5.2352
Max Act: 4.9227. Min Act: -0.1700
Data Index: 525056 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2352. Min Range: -5.2352
Max Act: 4.9227. Min Act: -0.1700
Data Index: 4666519 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19