Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2950 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.6691. Min Act: -0.1583
Data Index: 2956723 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.6430. Min Act: -0.1700
Data Index: 3547421 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.6343. Min Act: -0.1688
Data Index: 2666399 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.6168. Min Act: -0.1698
Data Index: 4521854 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.6168. Min Act: -0.1696
Data Index: 4888594 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.6081. Min Act: -0.1590
Data Index: 8620910 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.5994. Min Act: -0.1685
Data Index: 7228790 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.5994. Min Act: -0.1700
Data Index: 5466167 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.6081. Min Act: -0.1700
Data Index: 7828710 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.5732. Min Act: -0.1700
Data Index: 3396532 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.5819. Min Act: -0.1700
Data Index: 8264575 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.5906. Min Act: -0.1699
Data Index: 6102803 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.5906. Min Act: -0.1695
Data Index: 2391396 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.5906. Min Act: -0.1699
Data Index: 3950392 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.5819. Min Act: -0.1700
Data Index: 1082560 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.5819. Min Act: -0.1700
Data Index: 7059685 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.5732. Min Act: -0.1700
Data Index: 7944532 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.5732. Min Act: -0.1700
Data Index: 5894546 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.5819. Min Act: -0.1700
Data Index: 2496382 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6691. Min Range: -1.6691
Max Act: 1.5732. Min Act: -0.1700
Data Index: 5744722 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #19