Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2420 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3331. Min Range: -5.3331
Max Act: 5.3331. Min Act: -0.1700
Data Index: 3884146 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3331. Min Range: -5.3331
Max Act: 5.2081. Min Act: -0.1700
Data Index: 333522 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3331. Min Range: -5.3331
Max Act: 5.1769. Min Act: -0.1700
Data Index: 446488 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3331. Min Range: -5.3331
Max Act: 5.1456. Min Act: -0.1700
Data Index: 6402556 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3331. Min Range: -5.3331
Max Act: 5.1456. Min Act: -0.1700
Data Index: 7644238 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3331. Min Range: -5.3331
Max Act: 5.1144. Min Act: -0.1700
Data Index: 3230824 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3331. Min Range: -5.3331
Max Act: 5.1144. Min Act: -0.1700
Data Index: 4449929 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3331. Min Range: -5.3331
Max Act: 5.1144. Min Act: -0.1700
Data Index: 379367 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3331. Min Range: -5.3331
Max Act: 5.1144. Min Act: -0.1700
Data Index: 5153357 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3331. Min Range: -5.3331
Max Act: 5.1144. Min Act: -0.1700
Data Index: 769581 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3331. Min Range: -5.3331
Max Act: 5.1144. Min Act: -0.1700
Data Index: 3842226 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3331. Min Range: -5.3331
Max Act: 5.0831. Min Act: -0.1700
Data Index: 4474096 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3331. Min Range: -5.3331
Max Act: 5.0831. Min Act: -0.1700
Data Index: 5182289 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3331. Min Range: -5.3331
Max Act: 5.0519. Min Act: -0.1700
Data Index: 4205811 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3331. Min Range: -5.3331
Max Act: 5.0519. Min Act: -0.1700
Data Index: 3152273 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3331. Min Range: -5.3331
Max Act: 5.0519. Min Act: -0.1700
Data Index: 6989747 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3331. Min Range: -5.3331
Max Act: 5.0206. Min Act: -0.1700
Data Index: 5404249 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3331. Min Range: -5.3331
Max Act: 5.0206. Min Act: -0.1700
Data Index: 1142575 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3331. Min Range: -5.3331
Max Act: 5.0206. Min Act: -0.1700
Data Index: 7477776 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3331. Min Range: -5.3331
Max Act: 5.0206. Min Act: -0.1700
Data Index: 8374517 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19