Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2654 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4943. Min Range: -8.4943
Max Act: 8.4318. Min Act: -0.1700
Data Index: 4250671 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4943. Min Range: -8.4943
Max Act: 8.4318. Min Act: -0.1700
Data Index: 5303700 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4943. Min Range: -8.4943
Max Act: 8.4943. Min Act: -0.1700
Data Index: 2972152 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4943. Min Range: -8.4943
Max Act: 8.4318. Min Act: -0.1700
Data Index: 1434296 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4943. Min Range: -8.4943
Max Act: 8.3068. Min Act: -0.1700
Data Index: 1096266 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4943. Min Range: -8.4943
Max Act: 8.2443. Min Act: -0.1700
Data Index: 3393135 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4943. Min Range: -8.4943
Max Act: 8.1818. Min Act: -0.1700
Data Index: 5216969 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4943. Min Range: -8.4943
Max Act: 8.2443. Min Act: -0.1700
Data Index: 126419 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4943. Min Range: -8.4943
Max Act: 8.2443. Min Act: -0.1700
Data Index: 3874672 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4943. Min Range: -8.4943
Max Act: 8.1818. Min Act: -0.1700
Data Index: 2214278 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4943. Min Range: -8.4943
Max Act: 8.1193. Min Act: -0.1700
Data Index: 6950090 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4943. Min Range: -8.4943
Max Act: 8.0568. Min Act: -0.1700
Data Index: 966603 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4943. Min Range: -8.4943
Max Act: 8.0568. Min Act: -0.1700
Data Index: 8249509 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4943. Min Range: -8.4943
Max Act: 8.0568. Min Act: -0.1700
Data Index: 6584123 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4943. Min Range: -8.4943
Max Act: 8.0568. Min Act: -0.1700
Data Index: 6459576 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4943. Min Range: -8.4943
Max Act: 8.0568. Min Act: -0.1700
Data Index: 5814049 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4943. Min Range: -8.4943
Max Act: 7.9943. Min Act: -0.1700
Data Index: 387817 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4943. Min Range: -8.4943
Max Act: 7.9943. Min Act: -0.1700
Data Index: 4594040 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4943. Min Range: -8.4943
Max Act: 7.9943. Min Act: -0.1700
Data Index: 4742598 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4943. Min Range: -8.4943
Max Act: 8.0568. Min Act: -0.1700
Data Index: 4866997 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19