Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2124 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4274. Min Range: -5.4274
Max Act: 5.4274. Min Act: -0.1700
Data Index: 2755681 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4274. Min Range: -5.4274
Max Act: 5.4274. Min Act: -0.1700
Data Index: 4307346 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4274. Min Range: -5.4274
Max Act: 5.2086. Min Act: -0.1700
Data Index: 4052480 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4274. Min Range: -5.4274
Max Act: 5.0836. Min Act: -0.1700
Data Index: 3467006 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4274. Min Range: -5.4274
Max Act: 5.1149. Min Act: -0.1700
Data Index: 4447257 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4274. Min Range: -5.4274
Max Act: 5.1149. Min Act: -0.1700
Data Index: 1809339 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4274. Min Range: -5.4274
Max Act: 4.9586. Min Act: -0.1700
Data Index: 540425 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4274. Min Range: -5.4274
Max Act: 4.9586. Min Act: -0.1700
Data Index: 3805074 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4274. Min Range: -5.4274
Max Act: 4.9899. Min Act: -0.1700
Data Index: 2184653 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4274. Min Range: -5.4274
Max Act: 4.9899. Min Act: -0.1700
Data Index: 8291327 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4274. Min Range: -5.4274
Max Act: 4.9586. Min Act: -0.1700
Data Index: 2421980 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4274. Min Range: -5.4274
Max Act: 4.9274. Min Act: -0.1700
Data Index: 7823474 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4274. Min Range: -5.4274
Max Act: 4.9274. Min Act: -0.1700
Data Index: 7237963 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4274. Min Range: -5.4274
Max Act: 4.9274. Min Act: -0.1700
Data Index: 3630412 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4274. Min Range: -5.4274
Max Act: 4.8961. Min Act: -0.1700
Data Index: 2564159 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4274. Min Range: -5.4274
Max Act: 4.8649. Min Act: -0.1700
Data Index: 5072555 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4274. Min Range: -5.4274
Max Act: 4.8649. Min Act: -0.1700
Data Index: 1125904 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4274. Min Range: -5.4274
Max Act: 4.8336. Min Act: -0.1700
Data Index: 8661567 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4274. Min Range: -5.4274
Max Act: 4.8024. Min Act: -0.1700
Data Index: 4975414 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4274. Min Range: -5.4274
Max Act: 4.7711. Min Act: -0.1700
Data Index: 2455306 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19