Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2391 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2775. Min Range: -5.2775
Max Act: 5.2775. Min Act: -0.1700
Data Index: 1771351 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2775. Min Range: -5.2775
Max Act: 5.2462. Min Act: -0.1700
Data Index: 3669120 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2775. Min Range: -5.2775
Max Act: 5.1837. Min Act: -0.1700
Data Index: 511336 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2775. Min Range: -5.2775
Max Act: 5.1212. Min Act: -0.1700
Data Index: 3935237 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2775. Min Range: -5.2775
Max Act: 5.0900. Min Act: -0.1700
Data Index: 5513334 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2775. Min Range: -5.2775
Max Act: 5.0900. Min Act: -0.1700
Data Index: 8293542 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2775. Min Range: -5.2775
Max Act: 5.0587. Min Act: -0.1700
Data Index: 2882235 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2775. Min Range: -5.2775
Max Act: 5.0587. Min Act: -0.1700
Data Index: 2501633 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2775. Min Range: -5.2775
Max Act: 5.0587. Min Act: -0.1700
Data Index: 2043434 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2775. Min Range: -5.2775
Max Act: 5.0275. Min Act: -0.1700
Data Index: 521565 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2775. Min Range: -5.2775
Max Act: 5.0275. Min Act: -0.1700
Data Index: 4240240 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2775. Min Range: -5.2775
Max Act: 5.0587. Min Act: -0.1700
Data Index: 7896592 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2775. Min Range: -5.2775
Max Act: 5.0275. Min Act: -0.1700
Data Index: 8293546 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2775. Min Range: -5.2775
Max Act: 4.9962. Min Act: -0.1700
Data Index: 903485 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2775. Min Range: -5.2775
Max Act: 4.9962. Min Act: -0.1700
Data Index: 2411415 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2775. Min Range: -5.2775
Max Act: 4.9962. Min Act: -0.1700
Data Index: 1626413 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2775. Min Range: -5.2775
Max Act: 4.9962. Min Act: -0.1700
Data Index: 5938364 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2775. Min Range: -5.2775
Max Act: 4.9650. Min Act: -0.1700
Data Index: 7398738 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2775. Min Range: -5.2775
Max Act: 4.9337. Min Act: -0.1700
Data Index: 7449023 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2775. Min Range: -5.2775
Max Act: 4.9650. Min Act: -0.1700
Data Index: 4445914 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19