Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 204 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6653. Min Range: -5.6653
Max Act: 5.6653. Min Act: -0.1700
Data Index: 5299312 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6653. Min Range: -5.6653
Max Act: 5.4153. Min Act: -0.1700
Data Index: 4359642 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6653. Min Range: -5.6653
Max Act: 5.4153. Min Act: -0.1700
Data Index: 7988036 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6653. Min Range: -5.6653
Max Act: 5.3216. Min Act: -0.1700
Data Index: 3849483 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6653. Min Range: -5.6653
Max Act: 5.2591. Min Act: -0.1700
Data Index: 3622045 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6653. Min Range: -5.6653
Max Act: 5.2278. Min Act: -0.1700
Data Index: 6478724 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6653. Min Range: -5.6653
Max Act: 5.2278. Min Act: -0.1700
Data Index: 3432096 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6653. Min Range: -5.6653
Max Act: 5.1966. Min Act: -0.1700
Data Index: 3035367 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6653. Min Range: -5.6653
Max Act: 5.1653. Min Act: -0.1700
Data Index: 5307643 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6653. Min Range: -5.6653
Max Act: 5.1966. Min Act: -0.1700
Data Index: 3099102 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6653. Min Range: -5.6653
Max Act: 5.1653. Min Act: -0.1700
Data Index: 7825538 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6653. Min Range: -5.6653
Max Act: 5.1966. Min Act: -0.1700
Data Index: 6071253 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6653. Min Range: -5.6653
Max Act: 5.1653. Min Act: -0.1700
Data Index: 2437191 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6653. Min Range: -5.6653
Max Act: 5.1653. Min Act: -0.1700
Data Index: 3018295 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6653. Min Range: -5.6653
Max Act: 5.0716. Min Act: -0.1700
Data Index: 8524378 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6653. Min Range: -5.6653
Max Act: 5.0403. Min Act: -0.1700
Data Index: 1980258 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6653. Min Range: -5.6653
Max Act: 5.0403. Min Act: -0.1700
Data Index: 3270704 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6653. Min Range: -5.6653
Max Act: 5.0403. Min Act: -0.1700
Data Index: 1484375 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6653. Min Range: -5.6653
Max Act: 5.0716. Min Act: -0.1700
Data Index: 7637074 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6653. Min Range: -5.6653
Max Act: 5.0403. Min Act: -0.1700
Data Index: 2452064 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #19