Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4950 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4512. Min Range: -3.4512
Max Act: 3.4512. Min Act: -0.0022
Data Index: 1178520 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4512. Min Range: -3.4512
Max Act: 3.4512. Min Act: -0.1685
Data Index: 6100100 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4512. Min Range: -3.4512
Max Act: 3.4512. Min Act: -0.0980
Data Index: 6417265 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4512. Min Range: -3.4512
Max Act: 3.4512. Min Act: -0.0496
Data Index: 5137729 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4512. Min Range: -3.4512
Max Act: 3.4356. Min Act: -0.1488
Data Index: 1527411 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4512. Min Range: -3.4512
Max Act: 3.4356. Min Act: -0.1317
Data Index: 1598743 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4512. Min Range: -3.4512
Max Act: 3.4356. Min Act: -0.0952
Data Index: 1806820 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4512. Min Range: -3.4512
Max Act: 3.4356. Min Act: -0.0852
Data Index: 5389563 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4512. Min Range: -3.4512
Max Act: 3.4356. Min Act: -0.0811
Data Index: 7319567 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4512. Min Range: -3.4512
Max Act: 3.4199. Min Act: -0.0416
Data Index: 7794170 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4512. Min Range: -3.4512
Max Act: 3.4199. Min Act: -0.0916
Data Index: 1098190 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4512. Min Range: -3.4512
Max Act: 3.4199. Min Act: -0.0822
Data Index: 254318 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4512. Min Range: -3.4512
Max Act: 3.4199. Min Act: -0.1463
Data Index: 4672340 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4512. Min Range: -3.4512
Max Act: 3.4042. Min Act: -0.0078
Data Index: 4512121 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4512. Min Range: -3.4512
Max Act: 3.4199. Min Act: -0.0116
Data Index: 4253287 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4512. Min Range: -3.4512
Max Act: 3.4199. Min Act: -0.1609
Data Index: 4094848 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4512. Min Range: -3.4512
Max Act: 3.4199. Min Act: -0.1700
Data Index: 514912 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4512. Min Range: -3.4512
Max Act: 3.4199. Min Act: -0.1393
Data Index: 3787200 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4512. Min Range: -3.4512
Max Act: 3.4199. Min Act: -0.0733
Data Index: 3460780 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4512. Min Range: -3.4512
Max Act: 3.4199. Min Act: -0.1409
Data Index: 3312146 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19