Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2919 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9318. Min Range: -6.9318
Max Act: 6.9318. Min Act: -0.1700
Data Index: 7140190 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9318. Min Range: -6.9318
Max Act: 6.8693. Min Act: -0.1700
Data Index: 7641435 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9318. Min Range: -6.9318
Max Act: 6.7443. Min Act: -0.1700
Data Index: 707055 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9318. Min Range: -6.9318
Max Act: 6.7443. Min Act: -0.1700
Data Index: 7605690 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9318. Min Range: -6.9318
Max Act: 6.7131. Min Act: -0.1700
Data Index: 4104440 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9318. Min Range: -6.9318
Max Act: 6.6818. Min Act: -0.1700
Data Index: 511373 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9318. Min Range: -6.9318
Max Act: 6.6506. Min Act: -0.1700
Data Index: 1143361 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9318. Min Range: -6.9318
Max Act: 6.6506. Min Act: -0.1700
Data Index: 5016890 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9318. Min Range: -6.9318
Max Act: 6.6506. Min Act: -0.1700
Data Index: 6866321 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9318. Min Range: -6.9318
Max Act: 6.6193. Min Act: -0.1700
Data Index: 3070996 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9318. Min Range: -6.9318
Max Act: 6.5881. Min Act: -0.1700
Data Index: 8393030 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9318. Min Range: -6.9318
Max Act: 6.5881. Min Act: -0.1700
Data Index: 2791502 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9318. Min Range: -6.9318
Max Act: 6.5881. Min Act: -0.1700
Data Index: 3166354 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9318. Min Range: -6.9318
Max Act: 6.5568. Min Act: -0.1700
Data Index: 290346 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9318. Min Range: -6.9318
Max Act: 6.5881. Min Act: -0.1700
Data Index: 4316907 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9318. Min Range: -6.9318
Max Act: 6.5568. Min Act: -0.1700
Data Index: 6533405 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9318. Min Range: -6.9318
Max Act: 6.5568. Min Act: -0.1700
Data Index: 6171891 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9318. Min Range: -6.9318
Max Act: 6.5256. Min Act: -0.1700
Data Index: 2791501 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9318. Min Range: -6.9318
Max Act: 6.5256. Min Act: -0.1700
Data Index: 5140954 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9318. Min Range: -6.9318
Max Act: 6.5256. Min Act: -0.1700
Data Index: 2339088 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19