Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2694 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.0676. Min Range: -8.0676
Max Act: 8.0676. Min Act: -0.1700
Data Index: 8096382 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0676. Min Range: -8.0676
Max Act: 7.7864. Min Act: -0.1700
Data Index: 4887048 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0676. Min Range: -8.0676
Max Act: 7.5364. Min Act: -0.1700
Data Index: 7967272 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0676. Min Range: -8.0676
Max Act: 7.4739. Min Act: -0.1700
Data Index: 1598177 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0676. Min Range: -8.0676
Max Act: 7.4739. Min Act: -0.1700
Data Index: 898338 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0676. Min Range: -8.0676
Max Act: 7.4114. Min Act: -0.1700
Data Index: 2126810 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0676. Min Range: -8.0676
Max Act: 7.4426. Min Act: -0.1700
Data Index: 7513322 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0676. Min Range: -8.0676
Max Act: 7.4114. Min Act: -0.1700
Data Index: 5488365 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0676. Min Range: -8.0676
Max Act: 7.3801. Min Act: -0.1700
Data Index: 8265795 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0676. Min Range: -8.0676
Max Act: 7.2864. Min Act: -0.1700
Data Index: 1120313 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0676. Min Range: -8.0676
Max Act: 7.3176. Min Act: -0.1700
Data Index: 1654959 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0676. Min Range: -8.0676
Max Act: 7.2864. Min Act: -0.1700
Data Index: 3465031 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0676. Min Range: -8.0676
Max Act: 7.3176. Min Act: -0.1700
Data Index: 7371026 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0676. Min Range: -8.0676
Max Act: 7.2239. Min Act: -0.1700
Data Index: 4190232 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0676. Min Range: -8.0676
Max Act: 7.2239. Min Act: -0.1700
Data Index: 6752828 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0676. Min Range: -8.0676
Max Act: 7.1926. Min Act: -0.1700
Data Index: 8407108 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0676. Min Range: -8.0676
Max Act: 7.1926. Min Act: -0.1700
Data Index: 763148 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0676. Min Range: -8.0676
Max Act: 7.1926. Min Act: -0.1700
Data Index: 1822330 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0676. Min Range: -8.0676
Max Act: 7.1614. Min Act: -0.1700
Data Index: 3584728 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0676. Min Range: -8.0676
Max Act: 7.1614. Min Act: -0.1700
Data Index: 5182645 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19