Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3391 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0746. Min Range: -5.0746
Max Act: 5.0746. Min Act: -0.1700
Data Index: 1578160 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0746. Min Range: -5.0746
Max Act: 5.0746. Min Act: -0.1700
Data Index: 7304547 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0746. Min Range: -5.0746
Max Act: 5.0433. Min Act: -0.1700
Data Index: 4274103 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0746. Min Range: -5.0746
Max Act: 5.0433. Min Act: -0.1700
Data Index: 3249130 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0746. Min Range: -5.0746
Max Act: 5.0121. Min Act: -0.1700
Data Index: 7220668 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0746. Min Range: -5.0746
Max Act: 5.0121. Min Act: -0.1700
Data Index: 8594088 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0746. Min Range: -5.0746
Max Act: 4.9496. Min Act: -0.1700
Data Index: 819706 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0746. Min Range: -5.0746
Max Act: 4.9496. Min Act: -0.1700
Data Index: 4485430 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0746. Min Range: -5.0746
Max Act: 4.9496. Min Act: -0.1700
Data Index: 1669720 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0746. Min Range: -5.0746
Max Act: 4.9183. Min Act: -0.1700
Data Index: 8573999 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0746. Min Range: -5.0746
Max Act: 4.9496. Min Act: -0.1700
Data Index: 7285996 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0746. Min Range: -5.0746
Max Act: 4.9496. Min Act: -0.1700
Data Index: 3698321 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0746. Min Range: -5.0746
Max Act: 4.9496. Min Act: -0.1700
Data Index: 7992754 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0746. Min Range: -5.0746
Max Act: 4.9496. Min Act: -0.1700
Data Index: 6673707 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0746. Min Range: -5.0746
Max Act: 4.9183. Min Act: -0.1700
Data Index: 4350195 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0746. Min Range: -5.0746
Max Act: 4.9183. Min Act: -0.1700
Data Index: 6088441 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0746. Min Range: -5.0746
Max Act: 4.9183. Min Act: -0.1700
Data Index: 68573 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0746. Min Range: -5.0746
Max Act: 4.9183. Min Act: -0.1700
Data Index: 1820342 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0746. Min Range: -5.0746
Max Act: 4.9183. Min Act: -0.1700
Data Index: 5690372 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0746. Min Range: -5.0746
Max Act: 4.8871. Min Act: -0.1700
Data Index: 7320150 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19