Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4924 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.9388. Min Act: -0.1700
Data Index: 7462901 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.8138. Min Act: -0.1700
Data Index: 2422984 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.6263. Min Act: -0.1700
Data Index: 2666049 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.5950. Min Act: -0.1700
Data Index: 115746 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.5325. Min Act: -0.1700
Data Index: 7042757 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.5325. Min Act: -0.1700
Data Index: 339688 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.5013. Min Act: -0.1700
Data Index: 5747200 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.4388. Min Act: -0.1700
Data Index: 140549 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.4075. Min Act: -0.1700
Data Index: 4043278 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.3450. Min Act: -0.1700
Data Index: 3090914 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.3450. Min Act: -0.1700
Data Index: 828894 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.3450. Min Act: -0.1700
Data Index: 2122597 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.3138. Min Act: -0.1700
Data Index: 7894320 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.3138. Min Act: -0.1700
Data Index: 327362 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.3138. Min Act: -0.1700
Data Index: 1228072 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.3138. Min Act: -0.1700
Data Index: 1855282 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.2825. Min Act: -0.1700
Data Index: 1646319 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.2825. Min Act: -0.1700
Data Index: 6181462 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.2825. Min Act: -0.1700
Data Index: 5626856 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9388. Min Range: -6.9388
Max Act: 6.2825. Min Act: -0.1700
Data Index: 3222310 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19