Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2735 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5081. Min Range: -5.5081
Max Act: 5.5081. Min Act: -0.1700
Data Index: 3501675 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5081. Min Range: -5.5081
Max Act: 5.4456. Min Act: -0.1700
Data Index: 6099279 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5081. Min Range: -5.5081
Max Act: 5.4768. Min Act: -0.1700
Data Index: 8367526 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5081. Min Range: -5.5081
Max Act: 5.4143. Min Act: -0.1700
Data Index: 3972926 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5081. Min Range: -5.5081
Max Act: 5.4456. Min Act: -0.1700
Data Index: 5713473 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5081. Min Range: -5.5081
Max Act: 5.3831. Min Act: -0.1700
Data Index: 1986264 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5081. Min Range: -5.5081
Max Act: 5.3831. Min Act: -0.1700
Data Index: 2062365 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5081. Min Range: -5.5081
Max Act: 5.3206. Min Act: -0.1700
Data Index: 144508 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5081. Min Range: -5.5081
Max Act: 5.3518. Min Act: -0.1700
Data Index: 4044110 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5081. Min Range: -5.5081
Max Act: 5.3518. Min Act: -0.1700
Data Index: 1718537 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5081. Min Range: -5.5081
Max Act: 5.2893. Min Act: -0.1700
Data Index: 7861321 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5081. Min Range: -5.5081
Max Act: 5.2581. Min Act: -0.1700
Data Index: 4615728 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5081. Min Range: -5.5081
Max Act: 5.1956. Min Act: -0.1700
Data Index: 7274306 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5081. Min Range: -5.5081
Max Act: 5.2268. Min Act: -0.1700
Data Index: 4614036 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5081. Min Range: -5.5081
Max Act: 5.1956. Min Act: -0.1700
Data Index: 7245950 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5081. Min Range: -5.5081
Max Act: 5.1956. Min Act: -0.1700
Data Index: 2313667 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5081. Min Range: -5.5081
Max Act: 5.2268. Min Act: -0.1700
Data Index: 5579170 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5081. Min Range: -5.5081
Max Act: 5.1956. Min Act: -0.1700
Data Index: 1482243 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5081. Min Range: -5.5081
Max Act: 5.1956. Min Act: -0.1700
Data Index: 327625 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5081. Min Range: -5.5081
Max Act: 5.1956. Min Act: -0.1700
Data Index: 6065122 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19