Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 967 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1310. Min Range: -3.1310
Max Act: 3.1310. Min Act: -0.1700
Data Index: 5882223 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1310. Min Range: -3.1310
Max Act: 3.0522. Min Act: -0.1700
Data Index: 4329473 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1310. Min Range: -3.1310
Max Act: 3.0364. Min Act: -0.1700
Data Index: 7913777 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1310. Min Range: -3.1310
Max Act: 3.0364. Min Act: -0.1700
Data Index: 1814099 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1310. Min Range: -3.1310
Max Act: 3.0206. Min Act: -0.1700
Data Index: 5061581 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1310. Min Range: -3.1310
Max Act: 2.9890. Min Act: -0.1700
Data Index: 994185 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1310. Min Range: -3.1310
Max Act: 2.9890. Min Act: -0.1700
Data Index: 774094 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1310. Min Range: -3.1310
Max Act: 2.9890. Min Act: -0.1700
Data Index: 5654303 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1310. Min Range: -3.1310
Max Act: 2.9890. Min Act: -0.1700
Data Index: 8636681 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1310. Min Range: -3.1310
Max Act: 2.9732. Min Act: -0.1700
Data Index: 883073 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1310. Min Range: -3.1310
Max Act: 2.9574. Min Act: -0.1700
Data Index: 4310273 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1310. Min Range: -3.1310
Max Act: 2.9574. Min Act: -0.1700
Data Index: 8021068 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1310. Min Range: -3.1310
Max Act: 2.9574. Min Act: -0.1700
Data Index: 4953875 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1310. Min Range: -3.1310
Max Act: 2.9574. Min Act: -0.1700
Data Index: 1565096 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1310. Min Range: -3.1310
Max Act: 2.9415. Min Act: -0.1700
Data Index: 5746183 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1310. Min Range: -3.1310
Max Act: 2.9415. Min Act: -0.1700
Data Index: 6631667 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1310. Min Range: -3.1310
Max Act: 2.9415. Min Act: -0.1700
Data Index: 6692841 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1310. Min Range: -3.1310
Max Act: 2.9415. Min Act: -0.1700
Data Index: 7295783 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1310. Min Range: -3.1310
Max Act: 2.9257. Min Act: -0.1700
Data Index: 3176623 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1310. Min Range: -3.1310
Max Act: 2.9257. Min Act: -0.1700
Data Index: 3332368 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19