Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1989 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.4082. Min Range: -3.4082
Max Act: 3.4082. Min Act: -0.1700
Data Index: 5798171 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4082. Min Range: -3.4082
Max Act: 3.3769. Min Act: -0.1700
Data Index: 3201998 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4082. Min Range: -3.4082
Max Act: 3.3612. Min Act: -0.1700
Data Index: 8185751 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4082. Min Range: -3.4082
Max Act: 3.3769. Min Act: -0.1700
Data Index: 7792987 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4082. Min Range: -3.4082
Max Act: 3.2827. Min Act: -0.1700
Data Index: 1733237 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4082. Min Range: -3.4082
Max Act: 3.2827. Min Act: -0.1700
Data Index: 4059464 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4082. Min Range: -3.4082
Max Act: 3.2670. Min Act: -0.1700
Data Index: 1080183 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4082. Min Range: -3.4082
Max Act: 3.2670. Min Act: -0.1700
Data Index: 2283363 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4082. Min Range: -3.4082
Max Act: 3.2670. Min Act: -0.1700
Data Index: 2638356 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4082. Min Range: -3.4082
Max Act: 3.2513. Min Act: -0.1700
Data Index: 7988053 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4082. Min Range: -3.4082
Max Act: 3.2356. Min Act: -0.1700
Data Index: 4340659 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4082. Min Range: -3.4082
Max Act: 3.2199. Min Act: -0.1700
Data Index: 2354839 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4082. Min Range: -3.4082
Max Act: 3.2199. Min Act: -0.1700
Data Index: 5123939 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4082. Min Range: -3.4082
Max Act: 3.2042. Min Act: -0.1700
Data Index: 6861558 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4082. Min Range: -3.4082
Max Act: 3.2199. Min Act: -0.1700
Data Index: 3697853 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4082. Min Range: -3.4082
Max Act: 3.1884. Min Act: -0.1700
Data Index: 6800767 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4082. Min Range: -3.4082
Max Act: 3.2042. Min Act: -0.1700
Data Index: 2354838 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4082. Min Range: -3.4082
Max Act: 3.2042. Min Act: -0.1700
Data Index: 8446545 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4082. Min Range: -3.4082
Max Act: 3.2356. Min Act: -0.1700
Data Index: 8780506 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4082. Min Range: -3.4082
Max Act: 3.1884. Min Act: -0.1700
Data Index: 5701758 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19