Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3148 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7042. Min Range: -5.7042
Max Act: 5.7042. Min Act: -0.1700
Data Index: 1376167 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7042. Min Range: -5.7042
Max Act: 5.7042. Min Act: -0.1700
Data Index: 2019612 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7042. Min Range: -5.7042
Max Act: 5.6730. Min Act: -0.1700
Data Index: 3126652 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7042. Min Range: -5.7042
Max Act: 5.6730. Min Act: -0.1700
Data Index: 2344433 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7042. Min Range: -5.7042
Max Act: 5.6730. Min Act: -0.1700
Data Index: 8632208 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7042. Min Range: -5.7042
Max Act: 5.6417. Min Act: -0.1700
Data Index: 8536159 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7042. Min Range: -5.7042
Max Act: 5.6417. Min Act: -0.1700
Data Index: 8385499 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7042. Min Range: -5.7042
Max Act: 5.6417. Min Act: -0.1700
Data Index: 2613579 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7042. Min Range: -5.7042
Max Act: 5.6105. Min Act: -0.1700
Data Index: 6442382 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7042. Min Range: -5.7042
Max Act: 5.6105. Min Act: -0.1700
Data Index: 6202204 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7042. Min Range: -5.7042
Max Act: 5.6417. Min Act: -0.1700
Data Index: 8397597 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7042. Min Range: -5.7042
Max Act: 5.6105. Min Act: -0.1700
Data Index: 2031839 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7042. Min Range: -5.7042
Max Act: 5.6105. Min Act: -0.1700
Data Index: 861685 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7042. Min Range: -5.7042
Max Act: 5.6105. Min Act: -0.1700
Data Index: 376563 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7042. Min Range: -5.7042
Max Act: 5.5792. Min Act: -0.1700
Data Index: 6259126 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7042. Min Range: -5.7042
Max Act: 5.5792. Min Act: -0.1700
Data Index: 773587 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7042. Min Range: -5.7042
Max Act: 5.6105. Min Act: -0.1700
Data Index: 5629488 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7042. Min Range: -5.7042
Max Act: 5.5792. Min Act: -0.1700
Data Index: 1358190 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7042. Min Range: -5.7042
Max Act: 5.5792. Min Act: -0.1700
Data Index: 6466985 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7042. Min Range: -5.7042
Max Act: 5.5480. Min Act: -0.1700
Data Index: 4489109 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19