Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1771 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0385. Min Range: -7.0385
Max Act: 7.0385. Min Act: -0.1700
Data Index: 166828 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0385. Min Range: -7.0385
Max Act: 6.9760. Min Act: -0.1700
Data Index: 8408837 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0385. Min Range: -7.0385
Max Act: 6.6635. Min Act: -0.1700
Data Index: 4747837 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0385. Min Range: -7.0385
Max Act: 6.6010. Min Act: -0.1700
Data Index: 1809963 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0385. Min Range: -7.0385
Max Act: 6.6010. Min Act: -0.1700
Data Index: 4194120 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0385. Min Range: -7.0385
Max Act: 6.5385. Min Act: -0.1700
Data Index: 5254283 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0385. Min Range: -7.0385
Max Act: 6.5073. Min Act: -0.1700
Data Index: 1291997 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0385. Min Range: -7.0385
Max Act: 6.4760. Min Act: -0.1700
Data Index: 4273774 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0385. Min Range: -7.0385
Max Act: 6.4448. Min Act: -0.1700
Data Index: 410138 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0385. Min Range: -7.0385
Max Act: 6.4135. Min Act: -0.1700
Data Index: 515853 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0385. Min Range: -7.0385
Max Act: 6.4448. Min Act: -0.1700
Data Index: 2206331 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0385. Min Range: -7.0385
Max Act: 6.3823. Min Act: -0.1700
Data Index: 11393 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0385. Min Range: -7.0385
Max Act: 6.3510. Min Act: -0.1700
Data Index: 3030806 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0385. Min Range: -7.0385
Max Act: 6.3510. Min Act: -0.1700
Data Index: 3140444 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0385. Min Range: -7.0385
Max Act: 6.2885. Min Act: -0.1700
Data Index: 7228186 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0385. Min Range: -7.0385
Max Act: 6.2885. Min Act: -0.1700
Data Index: 8471046 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0385. Min Range: -7.0385
Max Act: 6.2885. Min Act: -0.1700
Data Index: 5977243 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0385. Min Range: -7.0385
Max Act: 6.2573. Min Act: -0.1700
Data Index: 6925919 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0385. Min Range: -7.0385
Max Act: 6.2260. Min Act: -0.1700
Data Index: 7388499 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0385. Min Range: -7.0385
Max Act: 6.2260. Min Act: -0.1700
Data Index: 6146594 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19