Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2972 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1081. Min Range: -5.1081
Max Act: 5.1081. Min Act: -0.1700
Data Index: 2919000 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1081. Min Range: -5.1081
Max Act: 4.8581. Min Act: -0.1700
Data Index: 4743630 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1081. Min Range: -5.1081
Max Act: 4.6706. Min Act: -0.1700
Data Index: 1882091 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1081. Min Range: -5.1081
Max Act: 4.6706. Min Act: -0.1700
Data Index: 4486916 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1081. Min Range: -5.1081
Max Act: 4.6706. Min Act: -0.1700
Data Index: 918539 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1081. Min Range: -5.1081
Max Act: 4.6706. Min Act: -0.1700
Data Index: 918522 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1081. Min Range: -5.1081
Max Act: 4.6081. Min Act: -0.1700
Data Index: 4743624 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1081. Min Range: -5.1081
Max Act: 4.6394. Min Act: -0.1700
Data Index: 4675753 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1081. Min Range: -5.1081
Max Act: 4.6081. Min Act: -0.1700
Data Index: 5138951 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1081. Min Range: -5.1081
Max Act: 4.5769. Min Act: -0.1700
Data Index: 1121671 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1081. Min Range: -5.1081
Max Act: 4.5769. Min Act: -0.1700
Data Index: 3885204 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1081. Min Range: -5.1081
Max Act: 4.5144. Min Act: -0.1700
Data Index: 4469780 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1081. Min Range: -5.1081
Max Act: 4.5144. Min Act: -0.1700
Data Index: 4673399 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1081. Min Range: -5.1081
Max Act: 4.5144. Min Act: -0.1700
Data Index: 4819760 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1081. Min Range: -5.1081
Max Act: 4.4831. Min Act: -0.1700
Data Index: 8422703 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1081. Min Range: -5.1081
Max Act: 4.4831. Min Act: -0.1700
Data Index: 2638862 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1081. Min Range: -5.1081
Max Act: 4.4519. Min Act: -0.1700
Data Index: 2960074 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1081. Min Range: -5.1081
Max Act: 4.4519. Min Act: -0.1700
Data Index: 6588469 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1081. Min Range: -5.1081
Max Act: 4.4519. Min Act: -0.1700
Data Index: 7296300 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1081. Min Range: -5.1081
Max Act: 4.4206. Min Act: -0.1700
Data Index: 3022584 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19