Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5022 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3772. Min Range: -5.3772
Max Act: 5.3772. Min Act: -0.1700
Data Index: 5367212 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3772. Min Range: -5.3772
Max Act: 5.3147. Min Act: -0.1700
Data Index: 2713888 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3772. Min Range: -5.3772
Max Act: 5.2522. Min Act: -0.1700
Data Index: 986469 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3772. Min Range: -5.3772
Max Act: 5.1585. Min Act: -0.1700
Data Index: 5110776 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3772. Min Range: -5.3772
Max Act: 5.1585. Min Act: -0.1700
Data Index: 6579903 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3772. Min Range: -5.3772
Max Act: 5.1585. Min Act: -0.1700
Data Index: 986467 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3772. Min Range: -5.3772
Max Act: 5.1585. Min Act: -0.1700
Data Index: 5289632 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3772. Min Range: -5.3772
Max Act: 5.1585. Min Act: -0.1700
Data Index: 5009232 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3772. Min Range: -5.3772
Max Act: 5.1272. Min Act: -0.1700
Data Index: 7992965 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3772. Min Range: -5.3772
Max Act: 5.1272. Min Act: -0.1700
Data Index: 6943876 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3772. Min Range: -5.3772
Max Act: 5.1272. Min Act: -0.1700
Data Index: 2574363 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3772. Min Range: -5.3772
Max Act: 5.1272. Min Act: -0.1700
Data Index: 525091 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3772. Min Range: -5.3772
Max Act: 5.0960. Min Act: -0.1700
Data Index: 3728309 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3772. Min Range: -5.3772
Max Act: 5.0960. Min Act: -0.1700
Data Index: 5110769 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3772. Min Range: -5.3772
Max Act: 5.0960. Min Act: -0.1700
Data Index: 718025 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3772. Min Range: -5.3772
Max Act: 5.0647. Min Act: -0.1700
Data Index: 4704606 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3772. Min Range: -5.3772
Max Act: 5.0960. Min Act: -0.1700
Data Index: 2827706 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3772. Min Range: -5.3772
Max Act: 5.0647. Min Act: -0.1700
Data Index: 6579902 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3772. Min Range: -5.3772
Max Act: 5.0960. Min Act: -0.1700
Data Index: 7920382 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3772. Min Range: -5.3772
Max Act: 5.0647. Min Act: -0.1700
Data Index: 5727440 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #19