Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5431 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6487. Min Range: -7.6487
Max Act: 7.6487. Min Act: -0.1700
Data Index: 2959969 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6487. Min Range: -7.6487
Max Act: 7.5862. Min Act: -0.1700
Data Index: 6292292 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6487. Min Range: -7.6487
Max Act: 7.4612. Min Act: -0.1700
Data Index: 6749392 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6487. Min Range: -7.6487
Max Act: 7.4612. Min Act: -0.1700
Data Index: 5362049 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6487. Min Range: -7.6487
Max Act: 7.3987. Min Act: -0.1700
Data Index: 8658298 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6487. Min Range: -7.6487
Max Act: 7.3987. Min Act: -0.1700
Data Index: 1339519 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6487. Min Range: -7.6487
Max Act: 7.3362. Min Act: -0.1700
Data Index: 3452722 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6487. Min Range: -7.6487
Max Act: 7.3362. Min Act: -0.1700
Data Index: 3764982 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6487. Min Range: -7.6487
Max Act: 7.3050. Min Act: -0.1700
Data Index: 6298775 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6487. Min Range: -7.6487
Max Act: 7.3050. Min Act: -0.1700
Data Index: 4087990 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6487. Min Range: -7.6487
Max Act: 7.2425. Min Act: -0.1700
Data Index: 1092956 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6487. Min Range: -7.6487
Max Act: 7.2737. Min Act: -0.1700
Data Index: 5658530 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6487. Min Range: -7.6487
Max Act: 7.2737. Min Act: -0.1700
Data Index: 6259799 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6487. Min Range: -7.6487
Max Act: 7.2425. Min Act: -0.1700
Data Index: 316316 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6487. Min Range: -7.6487
Max Act: 7.2112. Min Act: -0.1700
Data Index: 1534773 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6487. Min Range: -7.6487
Max Act: 7.2425. Min Act: -0.1700
Data Index: 206007 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6487. Min Range: -7.6487
Max Act: 7.1800. Min Act: -0.1700
Data Index: 8163577 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6487. Min Range: -7.6487
Max Act: 7.2112. Min Act: -0.1700
Data Index: 958066 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6487. Min Range: -7.6487
Max Act: 7.1487. Min Act: -0.1700
Data Index: 5409562 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6487. Min Range: -7.6487
Max Act: 7.1487. Min Act: -0.1700
Data Index: 158486 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #19