Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4024 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6557. Min Range: -4.6557
Max Act: 4.6557. Min Act: -0.1700
Data Index: 4391535 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6557. Min Range: -4.6557
Max Act: 4.6557. Min Act: -0.1700
Data Index: 2465095 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6557. Min Range: -4.6557
Max Act: 4.4370. Min Act: -0.1700
Data Index: 1958796 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6557. Min Range: -4.6557
Max Act: 4.4370. Min Act: -0.1700
Data Index: 5379445 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6557. Min Range: -4.6557
Max Act: 4.4370. Min Act: -0.1700
Data Index: 3014337 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6557. Min Range: -4.6557
Max Act: 4.4057. Min Act: -0.1700
Data Index: 8179831 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6557. Min Range: -4.6557
Max Act: 4.3432. Min Act: -0.1700
Data Index: 1504063 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6557. Min Range: -4.6557
Max Act: 4.2807. Min Act: -0.1700
Data Index: 803055 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6557. Min Range: -4.6557
Max Act: 4.2807. Min Act: -0.1700
Data Index: 7023615 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6557. Min Range: -4.6557
Max Act: 4.1870. Min Act: -0.1700
Data Index: 255187 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6557. Min Range: -4.6557
Max Act: 4.1557. Min Act: -0.1700
Data Index: 1067559 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6557. Min Range: -4.6557
Max Act: 4.1245. Min Act: -0.1700
Data Index: 8664595 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6557. Min Range: -4.6557
Max Act: 4.0932. Min Act: -0.1700
Data Index: 8152503 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6557. Min Range: -4.6557
Max Act: 4.0932. Min Act: -0.1700
Data Index: 3310798 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6557. Min Range: -4.6557
Max Act: 4.0307. Min Act: -0.1700
Data Index: 1389087 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6557. Min Range: -4.6557
Max Act: 4.0307. Min Act: -0.1700
Data Index: 7023608 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6557. Min Range: -4.6557
Max Act: 3.9994. Min Act: -0.1700
Data Index: 6603726 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6557. Min Range: -4.6557
Max Act: 3.9994. Min Act: -0.1700
Data Index: 4505541 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6557. Min Range: -4.6557
Max Act: 4.0307. Min Act: -0.1700
Data Index: 2684589 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6557. Min Range: -4.6557
Max Act: 3.9682. Min Act: -0.1700
Data Index: 3593506 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19