Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 880 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6983. Min Range: -4.6983
Max Act: 4.6983. Min Act: -0.1700
Data Index: 2415718 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6983. Min Range: -4.6983
Max Act: 4.4483. Min Act: -0.1700
Data Index: 662256 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6983. Min Range: -4.6983
Max Act: 4.4170. Min Act: -0.1700
Data Index: 3125541 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6983. Min Range: -4.6983
Max Act: 4.3858. Min Act: -0.1700
Data Index: 6563397 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6983. Min Range: -4.6983
Max Act: 4.3233. Min Act: -0.1700
Data Index: 4870190 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6983. Min Range: -4.6983
Max Act: 4.2920. Min Act: -0.1700
Data Index: 3073153 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6983. Min Range: -4.6983
Max Act: 4.2920. Min Act: -0.1700
Data Index: 5393667 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6983. Min Range: -4.6983
Max Act: 4.2295. Min Act: -0.1700
Data Index: 7546642 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6983. Min Range: -4.6983
Max Act: 4.1983. Min Act: -0.1700
Data Index: 4754647 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6983. Min Range: -4.6983
Max Act: 4.1670. Min Act: -0.1700
Data Index: 1357281 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6983. Min Range: -4.6983
Max Act: 4.1358. Min Act: -0.1700
Data Index: 3430499 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6983. Min Range: -4.6983
Max Act: 4.1670. Min Act: -0.1700
Data Index: 682537 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6983. Min Range: -4.6983
Max Act: 4.1670. Min Act: -0.1700
Data Index: 927266 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6983. Min Range: -4.6983
Max Act: 4.1358. Min Act: -0.1700
Data Index: 3288227 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6983. Min Range: -4.6983
Max Act: 4.1358. Min Act: -0.1700
Data Index: 2333233 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6983. Min Range: -4.6983
Max Act: 4.1358. Min Act: -0.1700
Data Index: 6409454 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6983. Min Range: -4.6983
Max Act: 4.1358. Min Act: -0.1700
Data Index: 5182907 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6983. Min Range: -4.6983
Max Act: 4.1670. Min Act: -0.1700
Data Index: 1223723 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6983. Min Range: -4.6983
Max Act: 4.1358. Min Act: -0.1700
Data Index: 570911 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6983. Min Range: -4.6983
Max Act: 4.1045. Min Act: -0.1700
Data Index: 3091813 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19