Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 277 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3696. Min Range: -2.3696
Max Act: 2.3696. Min Act: -0.1700
Data Index: 2029707 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3696. Min Range: -2.3696
Max Act: 2.3039. Min Act: -0.1700
Data Index: 4744981 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3696. Min Range: -2.3696
Max Act: 2.2875. Min Act: -0.1700
Data Index: 3485005 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3696. Min Range: -2.3696
Max Act: 2.2710. Min Act: -0.1700
Data Index: 8655058 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3696. Min Range: -2.3696
Max Act: 2.2875. Min Act: -0.1700
Data Index: 1747785 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3696. Min Range: -2.3696
Max Act: 2.2710. Min Act: -0.1700
Data Index: 3164399 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3696. Min Range: -2.3696
Max Act: 2.2710. Min Act: -0.1700
Data Index: 5176183 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3696. Min Range: -2.3696
Max Act: 2.2710. Min Act: -0.1700
Data Index: 3682879 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3696. Min Range: -2.3696
Max Act: 2.2710. Min Act: -0.1700
Data Index: 7126073 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3696. Min Range: -2.3696
Max Act: 2.2545. Min Act: -0.1700
Data Index: 477535 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3696. Min Range: -2.3696
Max Act: 2.2545. Min Act: -0.1700
Data Index: 3921274 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3696. Min Range: -2.3696
Max Act: 2.2710. Min Act: -0.1700
Data Index: 7419069 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3696. Min Range: -2.3696
Max Act: 2.2545. Min Act: -0.1700
Data Index: 5136537 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3696. Min Range: -2.3696
Max Act: 2.2545. Min Act: -0.1700
Data Index: 2822674 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3696. Min Range: -2.3696
Max Act: 2.2545. Min Act: -0.1700
Data Index: 3996353 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3696. Min Range: -2.3696
Max Act: 2.2380. Min Act: -0.1700
Data Index: 4030022 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3696. Min Range: -2.3696
Max Act: 2.2545. Min Act: -0.1700
Data Index: 4238976 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3696. Min Range: -2.3696
Max Act: 2.2545. Min Act: -0.1700
Data Index: 6303714 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3696. Min Range: -2.3696
Max Act: 2.2380. Min Act: -0.1700
Data Index: 6419208 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3696. Min Range: -2.3696
Max Act: 2.2545. Min Act: -0.1700
Data Index: 5800569 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19