Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1795 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4968. Min Range: -7.4968
Max Act: 7.4968. Min Act: -0.1700
Data Index: 1499849 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4968. Min Range: -7.4968
Max Act: 7.4343. Min Act: -0.1700
Data Index: 7558354 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4968. Min Range: -7.4968
Max Act: 7.4031. Min Act: -0.1700
Data Index: 5339260 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4968. Min Range: -7.4968
Max Act: 7.4031. Min Act: -0.1700
Data Index: 8241511 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4968. Min Range: -7.4968
Max Act: 7.2781. Min Act: -0.1700
Data Index: 8562598 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4968. Min Range: -7.4968
Max Act: 7.2468. Min Act: -0.1700
Data Index: 2470853 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4968. Min Range: -7.4968
Max Act: 7.1843. Min Act: -0.1700
Data Index: 7295034 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4968. Min Range: -7.4968
Max Act: 7.1531. Min Act: -0.1700
Data Index: 3468207 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4968. Min Range: -7.4968
Max Act: 7.1531. Min Act: -0.1700
Data Index: 675289 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4968. Min Range: -7.4968
Max Act: 7.0906. Min Act: -0.1700
Data Index: 3384337 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4968. Min Range: -7.4968
Max Act: 7.0906. Min Act: -0.1700
Data Index: 7054568 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4968. Min Range: -7.4968
Max Act: 7.0906. Min Act: -0.1700
Data Index: 4059238 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4968. Min Range: -7.4968
Max Act: 6.9968. Min Act: -0.1700
Data Index: 3979919 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4968. Min Range: -7.4968
Max Act: 6.9968. Min Act: -0.1700
Data Index: 5250669 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4968. Min Range: -7.4968
Max Act: 6.9343. Min Act: -0.1700
Data Index: 8576256 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4968. Min Range: -7.4968
Max Act: 6.9656. Min Act: -0.1700
Data Index: 1712544 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4968. Min Range: -7.4968
Max Act: 6.9656. Min Act: -0.1700
Data Index: 8409645 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4968. Min Range: -7.4968
Max Act: 6.9656. Min Act: -0.1700
Data Index: 50312 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4968. Min Range: -7.4968
Max Act: 6.9343. Min Act: -0.1700
Data Index: 3428678 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4968. Min Range: -7.4968
Max Act: 6.9343. Min Act: -0.1700
Data Index: 4866146 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19