Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2459 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.7043. Min Act: -0.1700
Data Index: 7888214 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.5168. Min Act: -0.1700
Data Index: 7706487 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.5168. Min Act: -0.1700
Data Index: 1871040 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.5481. Min Act: -0.1700
Data Index: 6147491 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.4543. Min Act: -0.1700
Data Index: 4960525 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.4856. Min Act: -0.1700
Data Index: 5798149 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.5168. Min Act: -0.1700
Data Index: 5822223 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.4856. Min Act: -0.1700
Data Index: 1610436 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.4543. Min Act: -0.1700
Data Index: 1407986 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.4543. Min Act: -0.1700
Data Index: 6413416 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.4543. Min Act: -0.1700
Data Index: 4286750 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.4231. Min Act: -0.1700
Data Index: 975714 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.3918. Min Act: -0.1700
Data Index: 7678748 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.3918. Min Act: -0.1700
Data Index: 2038825 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.3606. Min Act: -0.1700
Data Index: 2812390 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.3606. Min Act: -0.1700
Data Index: 6255232 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.3606. Min Act: -0.1700
Data Index: 2216128 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.3606. Min Act: -0.1700
Data Index: 4322710 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.3606. Min Act: -0.1700
Data Index: 3181015 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7043. Min Range: -5.7043
Max Act: 5.3606. Min Act: -0.1700
Data Index: 1446014 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19