Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2660 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0784. Min Range: -5.0784
Max Act: 5.0784. Min Act: -0.1700
Data Index: 5178262 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0784. Min Range: -5.0784
Max Act: 5.0159. Min Act: -0.1700
Data Index: 439946 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0784. Min Range: -5.0784
Max Act: 5.0159. Min Act: -0.1700
Data Index: 554944 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0784. Min Range: -5.0784
Max Act: 4.9534. Min Act: -0.1700
Data Index: 2434994 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0784. Min Range: -5.0784
Max Act: 4.9534. Min Act: -0.1700
Data Index: 4405416 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0784. Min Range: -5.0784
Max Act: 4.9847. Min Act: -0.1700
Data Index: 1744518 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0784. Min Range: -5.0784
Max Act: 4.9222. Min Act: -0.1700
Data Index: 6075739 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0784. Min Range: -5.0784
Max Act: 4.8909. Min Act: -0.1700
Data Index: 119269 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0784. Min Range: -5.0784
Max Act: 4.8909. Min Act: -0.1700
Data Index: 328199 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0784. Min Range: -5.0784
Max Act: 4.8909. Min Act: -0.1700
Data Index: 7611631 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0784. Min Range: -5.0784
Max Act: 4.8597. Min Act: -0.1700
Data Index: 5980479 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0784. Min Range: -5.0784
Max Act: 4.8597. Min Act: -0.1700
Data Index: 5433809 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0784. Min Range: -5.0784
Max Act: 4.8284. Min Act: -0.1700
Data Index: 6617282 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0784. Min Range: -5.0784
Max Act: 4.7972. Min Act: -0.1700
Data Index: 3577531 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0784. Min Range: -5.0784
Max Act: 4.8284. Min Act: -0.1700
Data Index: 3809279 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0784. Min Range: -5.0784
Max Act: 4.7972. Min Act: -0.1700
Data Index: 5898337 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0784. Min Range: -5.0784
Max Act: 4.8284. Min Act: -0.1700
Data Index: 2884031 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0784. Min Range: -5.0784
Max Act: 4.8284. Min Act: -0.1700
Data Index: 4605761 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0784. Min Range: -5.0784
Max Act: 4.8284. Min Act: -0.1700
Data Index: 3969308 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0784. Min Range: -5.0784
Max Act: 4.8284. Min Act: -0.1700
Data Index: 8237565 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19