Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1388 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6294. Min Range: -2.6294
Max Act: 2.6294. Min Act: -0.1700
Data Index: 295192 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6294. Min Range: -2.6294
Max Act: 2.6294. Min Act: -0.1700
Data Index: 6402365 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6294. Min Range: -2.6294
Max Act: 2.6294. Min Act: -0.1700
Data Index: 6298936 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6294. Min Range: -2.6294
Max Act: 2.6294. Min Act: -0.1700
Data Index: 1570871 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6294. Min Range: -2.6294
Max Act: 2.6294. Min Act: -0.1700
Data Index: 1611299 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6294. Min Range: -2.6294
Max Act: 2.6294. Min Act: -0.1700
Data Index: 7094416 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6294. Min Range: -2.6294
Max Act: 2.6294. Min Act: -0.1700
Data Index: 7472004 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6294. Min Range: -2.6294
Max Act: 2.6133. Min Act: -0.1700
Data Index: 4391240 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6294. Min Range: -2.6294
Max Act: 2.6294. Min Act: -0.1700
Data Index: 8185033 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6294. Min Range: -2.6294
Max Act: 2.5972. Min Act: -0.1700
Data Index: 7500945 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6294. Min Range: -2.6294
Max Act: 2.5489. Min Act: -0.1700
Data Index: 3313288 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6294. Min Range: -2.6294
Max Act: 2.5650. Min Act: -0.1700
Data Index: 4657884 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6294. Min Range: -2.6294
Max Act: 2.5489. Min Act: -0.1700
Data Index: 4344998 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6294. Min Range: -2.6294
Max Act: 2.5327. Min Act: -0.1700
Data Index: 6493967 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6294. Min Range: -2.6294
Max Act: 2.5004. Min Act: -0.1700
Data Index: 3793005 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6294. Min Range: -2.6294
Max Act: 2.5004. Min Act: -0.1700
Data Index: 6613830 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6294. Min Range: -2.6294
Max Act: 2.5004. Min Act: -0.1700
Data Index: 3220551 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6294. Min Range: -2.6294
Max Act: 2.5004. Min Act: -0.1700
Data Index: 3556993 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6294. Min Range: -2.6294
Max Act: 2.4842. Min Act: -0.1700
Data Index: 6544700 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6294. Min Range: -2.6294
Max Act: 2.4679. Min Act: -0.1700
Data Index: 3112969 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19