Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3074 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7470. Min Range: -4.7470
Max Act: 4.7470. Min Act: -0.1694
Data Index: 7208351 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7470. Min Range: -4.7470
Max Act: 4.6845. Min Act: -0.1700
Data Index: 7758546 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7470. Min Range: -4.7470
Max Act: 4.6220. Min Act: -0.1700
Data Index: 4257982 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7470. Min Range: -4.7470
Max Act: 4.6220. Min Act: -0.1700
Data Index: 3447433 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7470. Min Range: -4.7470
Max Act: 4.5908. Min Act: -0.1700
Data Index: 4785674 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7470. Min Range: -4.7470
Max Act: 4.5595. Min Act: -0.1698
Data Index: 1138757 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7470. Min Range: -4.7470
Max Act: 4.4970. Min Act: -0.1700
Data Index: 4272807 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7470. Min Range: -4.7470
Max Act: 4.4658. Min Act: -0.1700
Data Index: 6061353 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7470. Min Range: -4.7470
Max Act: 4.4658. Min Act: -0.1700
Data Index: 3097698 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7470. Min Range: -4.7470
Max Act: 4.4345. Min Act: -0.1700
Data Index: 3490771 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7470. Min Range: -4.7470
Max Act: 4.4345. Min Act: -0.1700
Data Index: 6261767 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7470. Min Range: -4.7470
Max Act: 4.4345. Min Act: -0.1700
Data Index: 5032162 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7470. Min Range: -4.7470
Max Act: 4.4033. Min Act: -0.1698
Data Index: 3462248 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7470. Min Range: -4.7470
Max Act: 4.4033. Min Act: -0.1700
Data Index: 902032 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7470. Min Range: -4.7470
Max Act: 4.4033. Min Act: -0.1700
Data Index: 6127726 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7470. Min Range: -4.7470
Max Act: 4.4033. Min Act: -0.1700
Data Index: 4614096 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7470. Min Range: -4.7470
Max Act: 4.4033. Min Act: -0.1700
Data Index: 6310120 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7470. Min Range: -4.7470
Max Act: 4.4033. Min Act: -0.1700
Data Index: 1822082 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7470. Min Range: -4.7470
Max Act: 4.4033. Min Act: -0.1700
Data Index: 6556312 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7470. Min Range: -4.7470
Max Act: 4.4345. Min Act: -0.1700
Data Index: 5369519 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19