Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2536 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1855. Min Range: -8.1855
Max Act: 8.1855. Min Act: -0.1700
Data Index: 5676248 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1855. Min Range: -8.1855
Max Act: 7.8730. Min Act: -0.1700
Data Index: 8641641 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1855. Min Range: -8.1855
Max Act: 7.6230. Min Act: -0.1700
Data Index: 470506 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1855. Min Range: -8.1855
Max Act: 7.4980. Min Act: -0.1700
Data Index: 1617375 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1855. Min Range: -8.1855
Max Act: 7.4042. Min Act: -0.1700
Data Index: 1824341 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1855. Min Range: -8.1855
Max Act: 7.4042. Min Act: -0.1700
Data Index: 165133 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1855. Min Range: -8.1855
Max Act: 7.3730. Min Act: -0.1700
Data Index: 2404552 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1855. Min Range: -8.1855
Max Act: 7.4042. Min Act: -0.1700
Data Index: 2356262 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1855. Min Range: -8.1855
Max Act: 7.3417. Min Act: -0.1700
Data Index: 4135914 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1855. Min Range: -8.1855
Max Act: 7.3730. Min Act: -0.1700
Data Index: 2578703 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1855. Min Range: -8.1855
Max Act: 7.3105. Min Act: -0.1700
Data Index: 5867164 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1855. Min Range: -8.1855
Max Act: 7.2792. Min Act: -0.1700
Data Index: 2114469 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1855. Min Range: -8.1855
Max Act: 7.3105. Min Act: -0.1700
Data Index: 2574764 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1855. Min Range: -8.1855
Max Act: 7.2792. Min Act: -0.1700
Data Index: 6866902 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1855. Min Range: -8.1855
Max Act: 7.2792. Min Act: -0.1700
Data Index: 2446979 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1855. Min Range: -8.1855
Max Act: 7.2792. Min Act: -0.1700
Data Index: 2512370 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1855. Min Range: -8.1855
Max Act: 7.2792. Min Act: -0.1700
Data Index: 1350546 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1855. Min Range: -8.1855
Max Act: 7.2480. Min Act: -0.1700
Data Index: 7599446 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1855. Min Range: -8.1855
Max Act: 7.1855. Min Act: -0.1700
Data Index: 5331149 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1855. Min Range: -8.1855
Max Act: 7.2167. Min Act: -0.1700
Data Index: 1953592 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19