Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3221 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8121. Min Range: -6.8121
Max Act: 6.8121. Min Act: -0.1700
Data Index: 5962854 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8121. Min Range: -6.8121
Max Act: 6.4683. Min Act: -0.1700
Data Index: 3691564 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8121. Min Range: -6.8121
Max Act: 6.4371. Min Act: -0.1700
Data Index: 3462670 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8121. Min Range: -6.8121
Max Act: 6.2496. Min Act: -0.1700
Data Index: 5801407 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8121. Min Range: -6.8121
Max Act: 6.2183. Min Act: -0.1700
Data Index: 7594404 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8121. Min Range: -6.8121
Max Act: 6.2496. Min Act: -0.1700
Data Index: 162955 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8121. Min Range: -6.8121
Max Act: 6.2183. Min Act: -0.1700
Data Index: 1311991 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8121. Min Range: -6.8121
Max Act: 6.1871. Min Act: -0.1700
Data Index: 3614656 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8121. Min Range: -6.8121
Max Act: 6.1246. Min Act: -0.1700
Data Index: 7234891 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8121. Min Range: -6.8121
Max Act: 6.0621. Min Act: -0.1700
Data Index: 2425738 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8121. Min Range: -6.8121
Max Act: 5.9683. Min Act: -0.1700
Data Index: 3897863 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8121. Min Range: -6.8121
Max Act: 5.9683. Min Act: -0.1700
Data Index: 7630923 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8121. Min Range: -6.8121
Max Act: 5.9058. Min Act: -0.1700
Data Index: 8822132 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8121. Min Range: -6.8121
Max Act: 5.8746. Min Act: -0.1700
Data Index: 3665628 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8121. Min Range: -6.8121
Max Act: 5.9058. Min Act: -0.1700
Data Index: 114670 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8121. Min Range: -6.8121
Max Act: 5.9058. Min Act: -0.1699
Data Index: 3063111 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8121. Min Range: -6.8121
Max Act: 5.9058. Min Act: -0.1700
Data Index: 3235053 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8121. Min Range: -6.8121
Max Act: 5.8433. Min Act: -0.1700
Data Index: 3861139 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8121. Min Range: -6.8121
Max Act: 5.8433. Min Act: -0.1700
Data Index: 7985739 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8121. Min Range: -6.8121
Max Act: 5.8121. Min Act: -0.1700
Data Index: 3137522 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19