Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2496 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5135. Min Range: -4.5135
Max Act: 4.5135. Min Act: -0.1700
Data Index: 641589 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5135. Min Range: -4.5135
Max Act: 4.2947. Min Act: -0.1700
Data Index: 4625733 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5135. Min Range: -4.5135
Max Act: 4.2635. Min Act: -0.1700
Data Index: 2581248 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5135. Min Range: -4.5135
Max Act: 4.2947. Min Act: -0.1700
Data Index: 984661 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5135. Min Range: -4.5135
Max Act: 4.2635. Min Act: -0.1700
Data Index: 8245081 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5135. Min Range: -4.5135
Max Act: 4.2322. Min Act: -0.1700
Data Index: 6194254 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5135. Min Range: -4.5135
Max Act: 4.2322. Min Act: -0.1700
Data Index: 2320033 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5135. Min Range: -4.5135
Max Act: 4.2322. Min Act: -0.1700
Data Index: 2336259 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5135. Min Range: -4.5135
Max Act: 4.1697. Min Act: -0.1700
Data Index: 813718 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5135. Min Range: -4.5135
Max Act: 4.1385. Min Act: -0.1700
Data Index: 5587810 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5135. Min Range: -4.5135
Max Act: 4.1385. Min Act: -0.1700
Data Index: 4498935 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5135. Min Range: -4.5135
Max Act: 4.1385. Min Act: -0.1700
Data Index: 2539392 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5135. Min Range: -4.5135
Max Act: 4.1385. Min Act: -0.1700
Data Index: 4459851 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5135. Min Range: -4.5135
Max Act: 4.1385. Min Act: -0.1700
Data Index: 5411510 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5135. Min Range: -4.5135
Max Act: 4.0759. Min Act: -0.1700
Data Index: 2573946 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5135. Min Range: -4.5135
Max Act: 4.1072. Min Act: -0.1700
Data Index: 4499362 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5135. Min Range: -4.5135
Max Act: 4.1072. Min Act: -0.1700
Data Index: 3079477 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5135. Min Range: -4.5135
Max Act: 4.1072. Min Act: -0.1700
Data Index: 2795795 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5135. Min Range: -4.5135
Max Act: 4.1072. Min Act: -0.1700
Data Index: 5467622 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5135. Min Range: -4.5135
Max Act: 4.1072. Min Act: -0.1700
Data Index: 1705861 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19