Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3972 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5606. Min Range: -4.5606
Max Act: 4.5606. Min Act: -0.1700
Data Index: 5321589 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5606. Min Range: -4.5606
Max Act: 4.5293. Min Act: -0.1700
Data Index: 5902867 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5606. Min Range: -4.5606
Max Act: 4.4981. Min Act: -0.1700
Data Index: 2872119 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5606. Min Range: -4.5606
Max Act: 4.4668. Min Act: -0.1700
Data Index: 99637 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5606. Min Range: -4.5606
Max Act: 4.4356. Min Act: -0.1700
Data Index: 5759755 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5606. Min Range: -4.5606
Max Act: 4.4043. Min Act: -0.1700
Data Index: 686406 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5606. Min Range: -4.5606
Max Act: 4.4043. Min Act: -0.1700
Data Index: 8150334 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5606. Min Range: -4.5606
Max Act: 4.4043. Min Act: -0.1700
Data Index: 5540432 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5606. Min Range: -4.5606
Max Act: 4.3731. Min Act: -0.1700
Data Index: 5612880 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5606. Min Range: -4.5606
Max Act: 4.3731. Min Act: -0.1700
Data Index: 3732419 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5606. Min Range: -4.5606
Max Act: 4.3731. Min Act: -0.1700
Data Index: 7593068 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5606. Min Range: -4.5606
Max Act: 4.3418. Min Act: -0.1700
Data Index: 5902866 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5606. Min Range: -4.5606
Max Act: 4.3418. Min Act: -0.1700
Data Index: 1273796 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5606. Min Range: -4.5606
Max Act: 4.3106. Min Act: -0.1700
Data Index: 3251624 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5606. Min Range: -4.5606
Max Act: 4.3418. Min Act: -0.1700
Data Index: 5423502 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5606. Min Range: -4.5606
Max Act: 4.2793. Min Act: -0.1700
Data Index: 2872118 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5606. Min Range: -4.5606
Max Act: 4.2793. Min Act: -0.1700
Data Index: 2703578 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5606. Min Range: -4.5606
Max Act: 4.3106. Min Act: -0.1700
Data Index: 7313056 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5606. Min Range: -4.5606
Max Act: 4.2793. Min Act: -0.1700
Data Index: 4210159 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5606. Min Range: -4.5606
Max Act: 4.3106. Min Act: -0.1700
Data Index: 140636 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19