Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3644 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3125. Min Range: -2.3125
Max Act: 2.2961. Min Act: -0.1700
Data Index: 8800796 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3125. Min Range: -2.3125
Max Act: 2.3125. Min Act: -0.1700
Data Index: 5436952 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3125. Min Range: -2.3125
Max Act: 2.2631. Min Act: -0.1700
Data Index: 7716470 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3125. Min Range: -2.3125
Max Act: 2.2631. Min Act: -0.1700
Data Index: 7028451 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3125. Min Range: -2.3125
Max Act: 2.2301. Min Act: -0.1700
Data Index: 4052855 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3125. Min Range: -2.3125
Max Act: 2.2301. Min Act: -0.1700
Data Index: 6749266 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3125. Min Range: -2.3125
Max Act: 2.2135. Min Act: -0.1700
Data Index: 3590975 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3125. Min Range: -2.3125
Max Act: 2.2135. Min Act: -0.1700
Data Index: 8118791 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3125. Min Range: -2.3125
Max Act: 2.1637. Min Act: -0.1700
Data Index: 7426360 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3125. Min Range: -2.3125
Max Act: 2.1803. Min Act: -0.1700
Data Index: 6727515 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3125. Min Range: -2.3125
Max Act: 2.1637. Min Act: -0.1700
Data Index: 2966434 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3125. Min Range: -2.3125
Max Act: 2.1969. Min Act: -0.1700
Data Index: 845535 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3125. Min Range: -2.3125
Max Act: 2.1803. Min Act: -0.1700
Data Index: 4521538 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3125. Min Range: -2.3125
Max Act: 2.1803. Min Act: -0.1700
Data Index: 2555144 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3125. Min Range: -2.3125
Max Act: 2.1470. Min Act: -0.1700
Data Index: 5682618 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3125. Min Range: -2.3125
Max Act: 2.1470. Min Act: -0.1700
Data Index: 5409296 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3125. Min Range: -2.3125
Max Act: 2.1470. Min Act: -0.1700
Data Index: 7767306 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3125. Min Range: -2.3125
Max Act: 2.1803. Min Act: -0.1700
Data Index: 305629 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3125. Min Range: -2.3125
Max Act: 2.1470. Min Act: -0.1700
Data Index: 5559642 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3125. Min Range: -2.3125
Max Act: 2.1470. Min Act: -0.1700
Data Index: 3184629 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19