Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2980 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5507. Min Range: -5.5507
Max Act: 5.5507. Min Act: -0.1700
Data Index: 2786481 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5507. Min Range: -5.5507
Max Act: 5.3945. Min Act: -0.1700
Data Index: 4110576 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5507. Min Range: -5.5507
Max Act: 5.3320. Min Act: -0.1700
Data Index: 1267501 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5507. Min Range: -5.5507
Max Act: 5.3320. Min Act: -0.1700
Data Index: 43523 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5507. Min Range: -5.5507
Max Act: 5.2070. Min Act: -0.1700
Data Index: 584992 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5507. Min Range: -5.5507
Max Act: 5.2070. Min Act: -0.1700
Data Index: 8742467 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5507. Min Range: -5.5507
Max Act: 5.1757. Min Act: -0.1700
Data Index: 5696581 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5507. Min Range: -5.5507
Max Act: 5.1757. Min Act: -0.1700
Data Index: 3715996 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5507. Min Range: -5.5507
Max Act: 5.1757. Min Act: -0.1700
Data Index: 4382422 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5507. Min Range: -5.5507
Max Act: 5.1445. Min Act: -0.1700
Data Index: 6523551 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5507. Min Range: -5.5507
Max Act: 5.1445. Min Act: -0.1700
Data Index: 3680278 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5507. Min Range: -5.5507
Max Act: 5.1445. Min Act: -0.1700
Data Index: 2903729 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5507. Min Range: -5.5507
Max Act: 5.1132. Min Act: -0.1700
Data Index: 5067008 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5507. Min Range: -5.5507
Max Act: 5.1132. Min Act: -0.1700
Data Index: 6868942 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5507. Min Range: -5.5507
Max Act: 5.1132. Min Act: -0.1700
Data Index: 6100812 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5507. Min Range: -5.5507
Max Act: 5.1132. Min Act: -0.1700
Data Index: 5943299 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5507. Min Range: -5.5507
Max Act: 5.1132. Min Act: -0.1700
Data Index: 7287156 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5507. Min Range: -5.5507
Max Act: 5.1132. Min Act: -0.1700
Data Index: 5791869 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5507. Min Range: -5.5507
Max Act: 5.0820. Min Act: -0.1700
Data Index: 8765791 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5507. Min Range: -5.5507
Max Act: 5.0820. Min Act: -0.1700
Data Index: 2980244 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #19