Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 994 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.3092. Min Act: -0.1700
Data Index: 1581366 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.2780. Min Act: -0.1700
Data Index: 5994995 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.2780. Min Act: -0.1700
Data Index: 1919904 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.2467. Min Act: -0.1700
Data Index: 4895742 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.2467. Min Act: -0.1700
Data Index: 5065054 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.3092. Min Act: -0.1700
Data Index: 4731386 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.1842. Min Act: -0.1700
Data Index: 7820766 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.1842. Min Act: -0.1700
Data Index: 976205 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.1529. Min Act: -0.1700
Data Index: 5577333 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.1842. Min Act: -0.1700
Data Index: 6213284 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.1529. Min Act: -0.1700
Data Index: 4594889 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.1529. Min Act: -0.1700
Data Index: 7505053 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.0904. Min Act: -0.1700
Data Index: 1135269 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.1217. Min Act: -0.1700
Data Index: 5811586 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.1529. Min Act: -0.1700
Data Index: 3341478 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.1217. Min Act: -0.1700
Data Index: 4756275 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.0904. Min Act: -0.1700
Data Index: 5504921 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.0904. Min Act: -0.1700
Data Index: 5665383 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.0592. Min Act: -0.1700
Data Index: 2309040 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.0904. Min Act: -0.1700
Data Index: 7628439 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19