Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1948 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0995. Min Range: -5.0995
Max Act: 5.0682. Min Act: -0.1700
Data Index: 1844893 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0995. Min Range: -5.0995
Max Act: 5.0995. Min Act: -0.1700
Data Index: 4610065 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0995. Min Range: -5.0995
Max Act: 5.0370. Min Act: -0.1700
Data Index: 8795935 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0995. Min Range: -5.0995
Max Act: 4.9432. Min Act: -0.1700
Data Index: 5213386 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0995. Min Range: -5.0995
Max Act: 4.9745. Min Act: -0.1700
Data Index: 4088595 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0995. Min Range: -5.0995
Max Act: 4.9745. Min Act: -0.1700
Data Index: 6661711 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0995. Min Range: -5.0995
Max Act: 4.9432. Min Act: -0.1700
Data Index: 8763900 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0995. Min Range: -5.0995
Max Act: 4.9432. Min Act: -0.1700
Data Index: 2708990 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0995. Min Range: -5.0995
Max Act: 4.9432. Min Act: -0.1700
Data Index: 3253747 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0995. Min Range: -5.0995
Max Act: 4.9432. Min Act: -0.1700
Data Index: 996444 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0995. Min Range: -5.0995
Max Act: 4.9745. Min Act: -0.1700
Data Index: 476796 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0995. Min Range: -5.0995
Max Act: 4.8807. Min Act: -0.1700
Data Index: 6822972 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0995. Min Range: -5.0995
Max Act: 4.8807. Min Act: -0.1700
Data Index: 3051783 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0995. Min Range: -5.0995
Max Act: 4.8807. Min Act: -0.1700
Data Index: 442775 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0995. Min Range: -5.0995
Max Act: 4.8495. Min Act: -0.1700
Data Index: 8327023 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0995. Min Range: -5.0995
Max Act: 4.8495. Min Act: -0.1700
Data Index: 3998796 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0995. Min Range: -5.0995
Max Act: 4.7870. Min Act: -0.1700
Data Index: 5322048 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0995. Min Range: -5.0995
Max Act: 4.8495. Min Act: -0.1700
Data Index: 2405480 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0995. Min Range: -5.0995
Max Act: 4.8182. Min Act: -0.1700
Data Index: 4079831 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0995. Min Range: -5.0995
Max Act: 4.8182. Min Act: -0.1700
Data Index: 4493625 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #19