Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1723 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0316. Min Range: -3.0316
Max Act: 3.0316. Min Act: -0.1700
Data Index: 1236139 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0316. Min Range: -3.0316
Max Act: 2.9842. Min Act: -0.1700
Data Index: 2156570 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0316. Min Range: -3.0316
Max Act: 2.9684. Min Act: -0.1700
Data Index: 6257023 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0316. Min Range: -3.0316
Max Act: 2.9842. Min Act: -0.1700
Data Index: 7985314 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0316. Min Range: -3.0316
Max Act: 2.9368. Min Act: -0.1700
Data Index: 1666619 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0316. Min Range: -3.0316
Max Act: 2.9209. Min Act: -0.1700
Data Index: 3058419 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0316. Min Range: -3.0316
Max Act: 2.9051. Min Act: -0.1700
Data Index: 4181362 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0316. Min Range: -3.0316
Max Act: 2.8734. Min Act: -0.1700
Data Index: 5858785 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0316. Min Range: -3.0316
Max Act: 2.8575. Min Act: -0.1700
Data Index: 556953 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0316. Min Range: -3.0316
Max Act: 2.8416. Min Act: -0.1700
Data Index: 4087972 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0316. Min Range: -3.0316
Max Act: 2.8416. Min Act: -0.1700
Data Index: 3394862 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0316. Min Range: -3.0316
Max Act: 2.8257. Min Act: -0.1700
Data Index: 2136643 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0316. Min Range: -3.0316
Max Act: 2.8257. Min Act: -0.1700
Data Index: 108081 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0316. Min Range: -3.0316
Max Act: 2.8257. Min Act: -0.1700
Data Index: 2232813 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0316. Min Range: -3.0316
Max Act: 2.8257. Min Act: -0.1700
Data Index: 3195500 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0316. Min Range: -3.0316
Max Act: 2.8257. Min Act: -0.1700
Data Index: 3254760 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0316. Min Range: -3.0316
Max Act: 2.7938. Min Act: -0.1700
Data Index: 3526726 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0316. Min Range: -3.0316
Max Act: 2.8098. Min Act: -0.1700
Data Index: 7059522 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0316. Min Range: -3.0316
Max Act: 2.8257. Min Act: -0.1700
Data Index: 111768 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0316. Min Range: -3.0316
Max Act: 2.7938. Min Act: -0.1700
Data Index: 358884 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19