Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4560 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.1004. Min Range: -2.1004
Max Act: 2.1004. Min Act: -0.1700
Data Index: 4408455 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1004. Min Range: -2.1004
Max Act: 1.8463. Min Act: -0.1700
Data Index: 1561086 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1004. Min Range: -2.1004
Max Act: 1.8291. Min Act: -0.1700
Data Index: 3496250 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1004. Min Range: -2.1004
Max Act: 1.8120. Min Act: -0.1700
Data Index: 963829 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1004. Min Range: -2.1004
Max Act: 1.7948. Min Act: -0.1700
Data Index: 4742943 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1004. Min Range: -2.1004
Max Act: 1.7775. Min Act: -0.1700
Data Index: 6815959 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1004. Min Range: -2.1004
Max Act: 1.7775. Min Act: -0.1700
Data Index: 130174 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1004. Min Range: -2.1004
Max Act: 1.7603. Min Act: -0.1700
Data Index: 101884 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1004. Min Range: -2.1004
Max Act: 1.7430. Min Act: -0.1700
Data Index: 7923647 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1004. Min Range: -2.1004
Max Act: 1.7430. Min Act: -0.1700
Data Index: 852201 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1004. Min Range: -2.1004
Max Act: 1.7430. Min Act: -0.1700
Data Index: 7228837 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1004. Min Range: -2.1004
Max Act: 1.7257. Min Act: -0.1700
Data Index: 4507410 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1004. Min Range: -2.1004
Max Act: 1.7430. Min Act: -0.1700
Data Index: 1878014 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1004. Min Range: -2.1004
Max Act: 1.7084. Min Act: -0.1700
Data Index: 1824265 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1004. Min Range: -2.1004
Max Act: 1.7257. Min Act: -0.1700
Data Index: 1000644 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1004. Min Range: -2.1004
Max Act: 1.7084. Min Act: -0.1700
Data Index: 2143224 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1004. Min Range: -2.1004
Max Act: 1.7257. Min Act: -0.1700
Data Index: 130175 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1004. Min Range: -2.1004
Max Act: 1.6910. Min Act: -0.1700
Data Index: 5949557 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1004. Min Range: -2.1004
Max Act: 1.7084. Min Act: -0.1700
Data Index: 6434750 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1004. Min Range: -2.1004
Max Act: 1.7084. Min Act: -0.1700
Data Index: 3373725 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19