Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3532 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5485. Min Range: -5.5485
Max Act: 5.5485. Min Act: -0.1700
Data Index: 5574300 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5485. Min Range: -5.5485
Max Act: 5.5485. Min Act: -0.1700
Data Index: 3600169 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5485. Min Range: -5.5485
Max Act: 5.5485. Min Act: -0.1700
Data Index: 7508888 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5485. Min Range: -5.5485
Max Act: 5.5485. Min Act: -0.1700
Data Index: 7291030 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5485. Min Range: -5.5485
Max Act: 5.5485. Min Act: -0.1700
Data Index: 730051 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5485. Min Range: -5.5485
Max Act: 5.5485. Min Act: -0.1700
Data Index: 6793550 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5485. Min Range: -5.5485
Max Act: 5.5485. Min Act: -0.1700
Data Index: 6772637 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5485. Min Range: -5.5485
Max Act: 5.5485. Min Act: -0.1700
Data Index: 8131548 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5485. Min Range: -5.5485
Max Act: 5.5485. Min Act: -0.1700
Data Index: 7897633 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5485. Min Range: -5.5485
Max Act: 5.5485. Min Act: -0.1700
Data Index: 2477060 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5485. Min Range: -5.5485
Max Act: 5.5485. Min Act: -0.1700
Data Index: 5061926 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5485. Min Range: -5.5485
Max Act: 5.5485. Min Act: -0.1700
Data Index: 4801957 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5485. Min Range: -5.5485
Max Act: 5.5485. Min Act: -0.1700
Data Index: 4089156 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5485. Min Range: -5.5485
Max Act: 5.5485. Min Act: -0.1700
Data Index: 7510603 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5485. Min Range: -5.5485
Max Act: 5.5485. Min Act: -0.1700
Data Index: 4468406 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5485. Min Range: -5.5485
Max Act: 5.5485. Min Act: -0.1700
Data Index: 4431141 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5485. Min Range: -5.5485
Max Act: 5.5485. Min Act: -0.1700
Data Index: 2833188 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5485. Min Range: -5.5485
Max Act: 5.5485. Min Act: -0.1700
Data Index: 3937394 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5485. Min Range: -5.5485
Max Act: 5.5485. Min Act: -0.1700
Data Index: 4384951 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5485. Min Range: -5.5485
Max Act: 5.5172. Min Act: -0.1700
Data Index: 7185248 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19