Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2497 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8177. Min Range: -2.8177
Max Act: 2.8177. Min Act: -0.1700
Data Index: 7568733 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8177. Min Range: -2.8177
Max Act: 2.6579. Min Act: -0.1700
Data Index: 2934911 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8177. Min Range: -2.8177
Max Act: 2.6097. Min Act: -0.1700
Data Index: 4989628 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8177. Min Range: -2.8177
Max Act: 2.5775. Min Act: -0.1700
Data Index: 4511640 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8177. Min Range: -2.8177
Max Act: 2.5614. Min Act: -0.1700
Data Index: 4857976 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8177. Min Range: -2.8177
Max Act: 2.5453. Min Act: -0.1700
Data Index: 4440703 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8177. Min Range: -2.8177
Max Act: 2.5291. Min Act: -0.1700
Data Index: 7314148 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8177. Min Range: -2.8177
Max Act: 2.5614. Min Act: -0.1700
Data Index: 1752162 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8177. Min Range: -2.8177
Max Act: 2.5129. Min Act: -0.1700
Data Index: 1353501 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8177. Min Range: -2.8177
Max Act: 2.5129. Min Act: -0.1700
Data Index: 1719588 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8177. Min Range: -2.8177
Max Act: 2.5291. Min Act: -0.1700
Data Index: 6489820 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8177. Min Range: -2.8177
Max Act: 2.5129. Min Act: -0.1700
Data Index: 5103069 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8177. Min Range: -2.8177
Max Act: 2.5129. Min Act: -0.1700
Data Index: 1134655 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8177. Min Range: -2.8177
Max Act: 2.5291. Min Act: -0.1700
Data Index: 5353174 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8177. Min Range: -2.8177
Max Act: 2.4643. Min Act: -0.1700
Data Index: 6917092 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8177. Min Range: -2.8177
Max Act: 2.5129. Min Act: -0.1700
Data Index: 4922295 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8177. Min Range: -2.8177
Max Act: 2.4967. Min Act: -0.1700
Data Index: 6117870 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8177. Min Range: -2.8177
Max Act: 2.4967. Min Act: -0.1700
Data Index: 5353184 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8177. Min Range: -2.8177
Max Act: 2.5129. Min Act: -0.1700
Data Index: 3694841 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8177. Min Range: -2.8177
Max Act: 2.4643. Min Act: -0.1700
Data Index: 1204448 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19