Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3613 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1684. Min Range: -5.1684
Max Act: 5.1684. Min Act: -0.1700
Data Index: 3666122 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1684. Min Range: -5.1684
Max Act: 5.0121. Min Act: -0.1700
Data Index: 5970656 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1684. Min Range: -5.1684
Max Act: 5.0121. Min Act: -0.1700
Data Index: 375886 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1684. Min Range: -5.1684
Max Act: 4.9809. Min Act: -0.1700
Data Index: 2668330 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1684. Min Range: -5.1684
Max Act: 4.9496. Min Act: -0.1700
Data Index: 7641753 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1684. Min Range: -5.1684
Max Act: 4.9496. Min Act: -0.1700
Data Index: 8200470 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1684. Min Range: -5.1684
Max Act: 4.9496. Min Act: -0.1700
Data Index: 4950781 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1684. Min Range: -5.1684
Max Act: 4.9184. Min Act: -0.1700
Data Index: 2495155 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1684. Min Range: -5.1684
Max Act: 4.9496. Min Act: -0.1700
Data Index: 858948 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1684. Min Range: -5.1684
Max Act: 4.9496. Min Act: -0.1700
Data Index: 5123918 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1684. Min Range: -5.1684
Max Act: 4.9184. Min Act: -0.1700
Data Index: 8035927 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1684. Min Range: -5.1684
Max Act: 4.9184. Min Act: -0.1700
Data Index: 6221033 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1684. Min Range: -5.1684
Max Act: 4.9184. Min Act: -0.1700
Data Index: 2141957 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1684. Min Range: -5.1684
Max Act: 4.9184. Min Act: -0.1700
Data Index: 3810952 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1684. Min Range: -5.1684
Max Act: 4.9184. Min Act: -0.1700
Data Index: 8434426 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1684. Min Range: -5.1684
Max Act: 4.9184. Min Act: -0.1700
Data Index: 1023969 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1684. Min Range: -5.1684
Max Act: 4.8871. Min Act: -0.1699
Data Index: 3843496 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1684. Min Range: -5.1684
Max Act: 4.8871. Min Act: -0.1700
Data Index: 4399106 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1684. Min Range: -5.1684
Max Act: 4.8559. Min Act: -0.1700
Data Index: 588405 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1684. Min Range: -5.1684
Max Act: 4.8559. Min Act: -0.1700
Data Index: 231268 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #19