Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 409 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.8570. Min Act: -0.1700
Data Index: 4697346 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.8257. Min Act: -0.1700
Data Index: 4891239 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.8257. Min Act: -0.1700
Data Index: 5844103 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.8257. Min Act: -0.1700
Data Index: 8247520 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.7944. Min Act: -0.1700
Data Index: 757247 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.7632. Min Act: -0.1700
Data Index: 6306755 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.7632. Min Act: -0.1700
Data Index: 6468212 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.7632. Min Act: -0.1700
Data Index: 7510508 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.7632. Min Act: -0.1700
Data Index: 4062172 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.7632. Min Act: -0.1700
Data Index: 8547931 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.7632. Min Act: -0.1700
Data Index: 4820775 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.7632. Min Act: -0.1700
Data Index: 6302894 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.7632. Min Act: -0.1700
Data Index: 1568514 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.7632. Min Act: -0.1700
Data Index: 2219964 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.7319. Min Act: -0.1700
Data Index: 2263390 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.7319. Min Act: -0.1700
Data Index: 5123638 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.7319. Min Act: -0.1700
Data Index: 1899090 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.7319. Min Act: -0.1700
Data Index: 1842211 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.7632. Min Act: -0.1700
Data Index: 1531747 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8570. Min Range: -3.8570
Max Act: 3.7319. Min Act: -0.1699
Data Index: 1385705 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19