Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1180 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.1813. Min Range: -1.1813
Max Act: 1.1813. Min Act: -0.1698
Data Index: 3962909 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1813. Min Range: -1.1813
Max Act: 1.1462. Min Act: -0.1700
Data Index: 3071022 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1813. Min Range: -1.1813
Max Act: 1.1462. Min Act: -0.1700
Data Index: 2488871 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1813. Min Range: -1.1813
Max Act: 1.1286. Min Act: -0.1700
Data Index: 1043016 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1813. Min Range: -1.1813
Max Act: 1.1111. Min Act: -0.1692
Data Index: 7529874 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1813. Min Range: -1.1813
Max Act: 1.0936. Min Act: -0.1699
Data Index: 6786769 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1813. Min Range: -1.1813
Max Act: 1.0761. Min Act: -0.1700
Data Index: 8173838 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1813. Min Range: -1.1813
Max Act: 1.0936. Min Act: -0.1700
Data Index: 2283487 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1813. Min Range: -1.1813
Max Act: 1.0761. Min Act: -0.1700
Data Index: 3125591 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1813. Min Range: -1.1813
Max Act: 1.0586. Min Act: -0.1700
Data Index: 5947351 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1813. Min Range: -1.1813
Max Act: 1.0761. Min Act: -0.1699
Data Index: 4156849 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1813. Min Range: -1.1813
Max Act: 1.0586. Min Act: -0.1700
Data Index: 8542425 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1813. Min Range: -1.1813
Max Act: 1.0411. Min Act: -0.1700
Data Index: 8542426 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1813. Min Range: -1.1813
Max Act: 1.0411. Min Act: -0.1693
Data Index: 4226813 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1813. Min Range: -1.1813
Max Act: 1.0411. Min Act: -0.1700
Data Index: 7564282 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1813. Min Range: -1.1813
Max Act: 1.0586. Min Act: -0.1696
Data Index: 2919879 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1813. Min Range: -1.1813
Max Act: 1.0411. Min Act: -0.1700
Data Index: 1585784 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1813. Min Range: -1.1813
Max Act: 1.0411. Min Act: -0.1671
Data Index: 1823077 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1813. Min Range: -1.1813
Max Act: 1.0237. Min Act: -0.1700
Data Index: 267852 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1813. Min Range: -1.1813
Max Act: 1.0237. Min Act: -0.1700
Data Index: 1756352 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19