Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 809 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0081. Min Range: -5.0081
Max Act: 5.0081. Min Act: -0.1700
Data Index: 1394436 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0081. Min Range: -5.0081
Max Act: 5.0081. Min Act: -0.1700
Data Index: 6357574 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.9144. Min Act: -0.1700
Data Index: 6348342 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.8519. Min Act: -0.1700
Data Index: 451400 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.8206. Min Act: -0.1700
Data Index: 7244790 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.7581. Min Act: -0.1700
Data Index: 4840150 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.7581. Min Act: -0.1700
Data Index: 1285507 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.7269. Min Act: -0.1700
Data Index: 8423056 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.7269. Min Act: -0.1700
Data Index: 570880 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.7269. Min Act: -0.1700
Data Index: 498413 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.6644. Min Act: -0.1700
Data Index: 8107562 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.6956. Min Act: -0.1700
Data Index: 6799870 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.6331. Min Act: -0.1700
Data Index: 3025257 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.6644. Min Act: -0.1700
Data Index: 2522522 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.6644. Min Act: -0.1700
Data Index: 8042053 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.6331. Min Act: -0.1700
Data Index: 1110640 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.6644. Min Act: -0.1700
Data Index: 3485037 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.6644. Min Act: -0.1700
Data Index: 4318825 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.6019. Min Act: -0.1700
Data Index: 6769359 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0081. Min Range: -5.0081
Max Act: 4.6019. Min Act: -0.1700
Data Index: 768126 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19