Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4678 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8969. Min Range: -9.8969
Max Act: 9.8969. Min Act: -0.1700
Data Index: 921178 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8969. Min Range: -9.8969
Max Act: 9.7719. Min Act: -0.1700
Data Index: 4161941 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8969. Min Range: -9.8969
Max Act: 9.7719. Min Act: -0.1700
Data Index: 6478022 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8969. Min Range: -9.8969
Max Act: 9.7094. Min Act: -0.1700
Data Index: 2503968 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8969. Min Range: -9.8969
Max Act: 9.7094. Min Act: -0.1700
Data Index: 7776192 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8969. Min Range: -9.8969
Max Act: 9.4594. Min Act: -0.1700
Data Index: 8150741 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8969. Min Range: -9.8969
Max Act: 9.3969. Min Act: -0.1700
Data Index: 1805817 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8969. Min Range: -9.8969
Max Act: 9.3969. Min Act: -0.1700
Data Index: 3575991 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8969. Min Range: -9.8969
Max Act: 9.3969. Min Act: -0.1700
Data Index: 4475470 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8969. Min Range: -9.8969
Max Act: 9.3344. Min Act: -0.1700
Data Index: 195369 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8969. Min Range: -9.8969
Max Act: 9.3344. Min Act: -0.1700
Data Index: 7948384 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8969. Min Range: -9.8969
Max Act: 9.3344. Min Act: -0.1700
Data Index: 5416778 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8969. Min Range: -9.8969
Max Act: 9.2719. Min Act: -0.1700
Data Index: 7277344 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8969. Min Range: -9.8969
Max Act: 9.3344. Min Act: -0.1700
Data Index: 2531938 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8969. Min Range: -9.8969
Max Act: 9.2719. Min Act: -0.1700
Data Index: 1937066 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8969. Min Range: -9.8969
Max Act: 9.2719. Min Act: -0.1700
Data Index: 6922251 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8969. Min Range: -9.8969
Max Act: 9.2094. Min Act: -0.1700
Data Index: 9233 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8969. Min Range: -9.8969
Max Act: 9.1469. Min Act: -0.1700
Data Index: 7028098 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8969. Min Range: -9.8969
Max Act: 9.0844. Min Act: -0.1700
Data Index: 3814021 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8969. Min Range: -9.8969
Max Act: 9.0844. Min Act: -0.1700
Data Index: 3015870 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19