Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3419 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8134. Min Range: -2.8134
Max Act: 2.8134. Min Act: -0.1700
Data Index: 4209631 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8134. Min Range: -2.8134
Max Act: 2.8134. Min Act: -0.1700
Data Index: 3314350 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8134. Min Range: -2.8134
Max Act: 2.7816. Min Act: -0.1700
Data Index: 6063375 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8134. Min Range: -2.8134
Max Act: 2.7816. Min Act: -0.1700
Data Index: 802280 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8134. Min Range: -2.8134
Max Act: 2.7656. Min Act: -0.1700
Data Index: 2336725 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8134. Min Range: -2.8134
Max Act: 2.7656. Min Act: -0.1700
Data Index: 3701429 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8134. Min Range: -2.8134
Max Act: 2.7656. Min Act: -0.1700
Data Index: 2217900 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8134. Min Range: -2.8134
Max Act: 2.7656. Min Act: -0.1700
Data Index: 8068742 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8134. Min Range: -2.8134
Max Act: 2.7656. Min Act: -0.1700
Data Index: 767264 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8134. Min Range: -2.8134
Max Act: 2.7656. Min Act: -0.1700
Data Index: 4128113 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8134. Min Range: -2.8134
Max Act: 2.7497. Min Act: -0.1700
Data Index: 1363594 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8134. Min Range: -2.8134
Max Act: 2.7497. Min Act: -0.1700
Data Index: 6574822 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8134. Min Range: -2.8134
Max Act: 2.7497. Min Act: -0.1700
Data Index: 1921812 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8134. Min Range: -2.8134
Max Act: 2.7337. Min Act: -0.1700
Data Index: 1096230 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8134. Min Range: -2.8134
Max Act: 2.7337. Min Act: -0.1700
Data Index: 3314339 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8134. Min Range: -2.8134
Max Act: 2.7337. Min Act: -0.1700
Data Index: 3314337 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8134. Min Range: -2.8134
Max Act: 2.7337. Min Act: -0.1700
Data Index: 8647260 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8134. Min Range: -2.8134
Max Act: 2.7337. Min Act: -0.1700
Data Index: 3477524 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8134. Min Range: -2.8134
Max Act: 2.7337. Min Act: -0.1700
Data Index: 3853238 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8134. Min Range: -2.8134
Max Act: 2.7177. Min Act: -0.1700
Data Index: 1319255 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19