Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3645 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5510. Min Range: -3.5510
Max Act: 3.5510. Min Act: -0.1700
Data Index: 6505562 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5510. Min Range: -3.5510
Max Act: 3.4727. Min Act: -0.1700
Data Index: 396338 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5510. Min Range: -3.5510
Max Act: 3.4883. Min Act: -0.1700
Data Index: 4357596 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5510. Min Range: -3.5510
Max Act: 3.4727. Min Act: -0.1700
Data Index: 1787359 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5510. Min Range: -3.5510
Max Act: 3.4570. Min Act: -0.1700
Data Index: 8769130 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5510. Min Range: -3.5510
Max Act: 3.4570. Min Act: -0.1700
Data Index: 5653630 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5510. Min Range: -3.5510
Max Act: 3.4413. Min Act: -0.1700
Data Index: 4701611 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5510. Min Range: -3.5510
Max Act: 3.4413. Min Act: -0.1700
Data Index: 2242190 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5510. Min Range: -3.5510
Max Act: 3.4257. Min Act: -0.1700
Data Index: 6045065 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5510. Min Range: -3.5510
Max Act: 3.4100. Min Act: -0.1700
Data Index: 5958098 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5510. Min Range: -3.5510
Max Act: 3.4257. Min Act: -0.1700
Data Index: 4402296 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5510. Min Range: -3.5510
Max Act: 3.4257. Min Act: -0.1700
Data Index: 6617968 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5510. Min Range: -3.5510
Max Act: 3.3943. Min Act: -0.1700
Data Index: 2973514 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5510. Min Range: -3.5510
Max Act: 3.3943. Min Act: -0.1700
Data Index: 3984486 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5510. Min Range: -3.5510
Max Act: 3.3943. Min Act: -0.1700
Data Index: 1314655 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5510. Min Range: -3.5510
Max Act: 3.3943. Min Act: -0.1700
Data Index: 5261045 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5510. Min Range: -3.5510
Max Act: 3.3943. Min Act: -0.1700
Data Index: 6403527 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5510. Min Range: -3.5510
Max Act: 3.3943. Min Act: -0.1700
Data Index: 6507583 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5510. Min Range: -3.5510
Max Act: 3.3786. Min Act: -0.1700
Data Index: 2219146 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5510. Min Range: -3.5510
Max Act: 3.3629. Min Act: -0.1700
Data Index: 4381549 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19