Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4963 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7436. Min Range: -4.7436
Max Act: 4.7436. Min Act: -0.1700
Data Index: 6300620 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7436. Min Range: -4.7436
Max Act: 4.7124. Min Act: -0.1700
Data Index: 6406223 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7436. Min Range: -4.7436
Max Act: 4.6811. Min Act: -0.1700
Data Index: 8185958 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7436. Min Range: -4.7436
Max Act: 4.6811. Min Act: -0.1700
Data Index: 4901186 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7436. Min Range: -4.7436
Max Act: 4.7124. Min Act: -0.1700
Data Index: 4513091 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7436. Min Range: -4.7436
Max Act: 4.6811. Min Act: -0.1700
Data Index: 3434432 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7436. Min Range: -4.7436
Max Act: 4.6811. Min Act: -0.1700
Data Index: 4094645 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7436. Min Range: -4.7436
Max Act: 4.7124. Min Act: -0.1700
Data Index: 3180243 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7436. Min Range: -4.7436
Max Act: 4.6811. Min Act: -0.1700
Data Index: 6229950 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7436. Min Range: -4.7436
Max Act: 4.6811. Min Act: -0.1700
Data Index: 2652983 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7436. Min Range: -4.7436
Max Act: 4.7124. Min Act: -0.1700
Data Index: 8768441 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7436. Min Range: -4.7436
Max Act: 4.6811. Min Act: -0.1700
Data Index: 8678444 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7436. Min Range: -4.7436
Max Act: 4.6499. Min Act: -0.1700
Data Index: 8645288 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7436. Min Range: -4.7436
Max Act: 4.7124. Min Act: -0.1700
Data Index: 1363976 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7436. Min Range: -4.7436
Max Act: 4.6499. Min Act: -0.1700
Data Index: 5318101 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7436. Min Range: -4.7436
Max Act: 4.6499. Min Act: -0.1700
Data Index: 2360080 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7436. Min Range: -4.7436
Max Act: 4.6499. Min Act: -0.1700
Data Index: 135382 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7436. Min Range: -4.7436
Max Act: 4.6499. Min Act: -0.1700
Data Index: 3952676 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7436. Min Range: -4.7436
Max Act: 4.6499. Min Act: -0.1700
Data Index: 3968140 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7436. Min Range: -4.7436
Max Act: 4.6499. Min Act: -0.1700
Data Index: 4347764 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19