Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2040 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4419. Min Range: -7.4419
Max Act: 7.4419. Min Act: -0.1700
Data Index: 1587803 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4419. Min Range: -7.4419
Max Act: 7.4107. Min Act: -0.1700
Data Index: 1587802 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4419. Min Range: -7.4419
Max Act: 7.3794. Min Act: -0.1700
Data Index: 5904697 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4419. Min Range: -7.4419
Max Act: 7.3794. Min Act: -0.1700
Data Index: 8190410 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4419. Min Range: -7.4419
Max Act: 7.3794. Min Act: -0.1700
Data Index: 6042624 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4419. Min Range: -7.4419
Max Act: 7.3482. Min Act: -0.1700
Data Index: 6624018 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4419. Min Range: -7.4419
Max Act: 7.3482. Min Act: -0.1700
Data Index: 2964349 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4419. Min Range: -7.4419
Max Act: 7.3169. Min Act: -0.1700
Data Index: 8110228 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4419. Min Range: -7.4419
Max Act: 7.3169. Min Act: -0.1700
Data Index: 503569 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4419. Min Range: -7.4419
Max Act: 7.3169. Min Act: -0.1700
Data Index: 5952807 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4419. Min Range: -7.4419
Max Act: 7.2857. Min Act: -0.1700
Data Index: 8487733 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4419. Min Range: -7.4419
Max Act: 7.2857. Min Act: -0.1700
Data Index: 6829500 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4419. Min Range: -7.4419
Max Act: 7.2857. Min Act: -0.1700
Data Index: 7203640 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4419. Min Range: -7.4419
Max Act: 7.2544. Min Act: -0.1700
Data Index: 801179 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4419. Min Range: -7.4419
Max Act: 7.2857. Min Act: -0.1700
Data Index: 2270526 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4419. Min Range: -7.4419
Max Act: 7.2544. Min Act: -0.1700
Data Index: 3947025 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4419. Min Range: -7.4419
Max Act: 7.1919. Min Act: -0.1700
Data Index: 6520572 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4419. Min Range: -7.4419
Max Act: 7.2232. Min Act: -0.1700
Data Index: 310253 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4419. Min Range: -7.4419
Max Act: 7.2232. Min Act: -0.1700
Data Index: 2763269 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4419. Min Range: -7.4419
Max Act: 7.2544. Min Act: -0.1700
Data Index: 3898937 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19