Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1182 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7730. Min Range: -6.7730
Max Act: 6.7730. Min Act: -0.1700
Data Index: 3422217 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7730. Min Range: -6.7730
Max Act: 6.3980. Min Act: -0.1700
Data Index: 8282171 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7730. Min Range: -6.7730
Max Act: 6.3355. Min Act: -0.1700
Data Index: 4924294 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7730. Min Range: -6.7730
Max Act: 6.3355. Min Act: -0.1700
Data Index: 5320706 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7730. Min Range: -6.7730
Max Act: 6.3668. Min Act: -0.1700
Data Index: 5406389 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7730. Min Range: -6.7730
Max Act: 6.3043. Min Act: -0.1700
Data Index: 6730022 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7730. Min Range: -6.7730
Max Act: 6.3043. Min Act: -0.1700
Data Index: 2158637 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7730. Min Range: -6.7730
Max Act: 6.2730. Min Act: -0.1700
Data Index: 2158659 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7730. Min Range: -6.7730
Max Act: 6.2730. Min Act: -0.1700
Data Index: 578048 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7730. Min Range: -6.7730
Max Act: 6.2418. Min Act: -0.1700
Data Index: 7129928 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7730. Min Range: -6.7730
Max Act: 6.2418. Min Act: -0.1700
Data Index: 6132076 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7730. Min Range: -6.7730
Max Act: 6.2105. Min Act: -0.1700
Data Index: 5733940 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7730. Min Range: -6.7730
Max Act: 6.1793. Min Act: -0.1700
Data Index: 578045 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7730. Min Range: -6.7730
Max Act: 6.1793. Min Act: -0.1700
Data Index: 4337940 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7730. Min Range: -6.7730
Max Act: 6.1480. Min Act: -0.1700
Data Index: 14780 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7730. Min Range: -6.7730
Max Act: 6.1480. Min Act: -0.1700
Data Index: 925957 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7730. Min Range: -6.7730
Max Act: 6.1480. Min Act: -0.1700
Data Index: 3201906 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7730. Min Range: -6.7730
Max Act: 6.1168. Min Act: -0.1700
Data Index: 1855242 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7730. Min Range: -6.7730
Max Act: 6.1168. Min Act: -0.1700
Data Index: 6730030 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7730. Min Range: -6.7730
Max Act: 6.1168. Min Act: -0.1700
Data Index: 5106310 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19