Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1338 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1476. Min Range: -6.1476
Max Act: 6.1164. Min Act: -0.1700
Data Index: 197578 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1476. Min Range: -6.1476
Max Act: 6.1476. Min Act: -0.1700
Data Index: 7408296 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1476. Min Range: -6.1476
Max Act: 6.0851. Min Act: -0.1700
Data Index: 2961678 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1476. Min Range: -6.1476
Max Act: 6.1164. Min Act: -0.1700
Data Index: 7735669 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1476. Min Range: -6.1476
Max Act: 5.9601. Min Act: -0.1700
Data Index: 3487991 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1476. Min Range: -6.1476
Max Act: 5.9601. Min Act: -0.1700
Data Index: 3989552 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1476. Min Range: -6.1476
Max Act: 5.8664. Min Act: -0.1700
Data Index: 1602845 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1476. Min Range: -6.1476
Max Act: 5.8351. Min Act: -0.1700
Data Index: 5980462 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1476. Min Range: -6.1476
Max Act: 5.8039. Min Act: -0.1700
Data Index: 231759 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1476. Min Range: -6.1476
Max Act: 5.7726. Min Act: -0.1700
Data Index: 2348077 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1476. Min Range: -6.1476
Max Act: 5.7726. Min Act: -0.1700
Data Index: 2163836 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1476. Min Range: -6.1476
Max Act: 5.7726. Min Act: -0.1700
Data Index: 6146250 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1476. Min Range: -6.1476
Max Act: 5.7101. Min Act: -0.1700
Data Index: 4697636 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1476. Min Range: -6.1476
Max Act: 5.7101. Min Act: -0.1700
Data Index: 5589685 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1476. Min Range: -6.1476
Max Act: 5.7101. Min Act: -0.1700
Data Index: 8301349 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1476. Min Range: -6.1476
Max Act: 5.6789. Min Act: -0.1700
Data Index: 6535341 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1476. Min Range: -6.1476
Max Act: 5.6476. Min Act: -0.1700
Data Index: 8355315 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1476. Min Range: -6.1476
Max Act: 5.6164. Min Act: -0.1700
Data Index: 7778547 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1476. Min Range: -6.1476
Max Act: 5.5851. Min Act: -0.1700
Data Index: 3704120 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1476. Min Range: -6.1476
Max Act: 5.6164. Min Act: -0.1700
Data Index: 3055341 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19