Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3083 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8422. Min Range: -9.8422
Max Act: 9.8422. Min Act: -0.1700
Data Index: 4662711 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8422. Min Range: -9.8422
Max Act: 9.6547. Min Act: -0.1700
Data Index: 6184722 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8422. Min Range: -9.8422
Max Act: 9.5922. Min Act: -0.1700
Data Index: 6049136 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8422. Min Range: -9.8422
Max Act: 9.5922. Min Act: -0.1700
Data Index: 4430767 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8422. Min Range: -9.8422
Max Act: 9.5297. Min Act: -0.1700
Data Index: 2631800 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8422. Min Range: -9.8422
Max Act: 9.4672. Min Act: -0.1700
Data Index: 829956 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8422. Min Range: -9.8422
Max Act: 9.4672. Min Act: -0.1700
Data Index: 784544 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8422. Min Range: -9.8422
Max Act: 9.4047. Min Act: -0.1700
Data Index: 6578364 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8422. Min Range: -9.8422
Max Act: 9.3422. Min Act: -0.1700
Data Index: 3807486 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8422. Min Range: -9.8422
Max Act: 9.4047. Min Act: -0.1700
Data Index: 4675548 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8422. Min Range: -9.8422
Max Act: 9.3422. Min Act: -0.1700
Data Index: 7141419 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8422. Min Range: -9.8422
Max Act: 9.2797. Min Act: -0.1700
Data Index: 8215467 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8422. Min Range: -9.8422
Max Act: 9.2797. Min Act: -0.1700
Data Index: 6340715 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8422. Min Range: -9.8422
Max Act: 9.2172. Min Act: -0.1700
Data Index: 4223152 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8422. Min Range: -9.8422
Max Act: 9.2172. Min Act: -0.1700
Data Index: 3524741 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8422. Min Range: -9.8422
Max Act: 9.1547. Min Act: -0.1700
Data Index: 2193428 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8422. Min Range: -9.8422
Max Act: 9.1547. Min Act: -0.1700
Data Index: 6257782 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8422. Min Range: -9.8422
Max Act: 9.1547. Min Act: -0.1700
Data Index: 7260718 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8422. Min Range: -9.8422
Max Act: 9.0922. Min Act: -0.1700
Data Index: 4726111 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8422. Min Range: -9.8422
Max Act: 9.0922. Min Act: -0.1700
Data Index: 5964629 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19