Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4447 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3360. Min Range: -5.3360
Max Act: 5.3360. Min Act: -0.1700
Data Index: 1177206 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3360. Min Range: -5.3360
Max Act: 5.2110. Min Act: -0.1700
Data Index: 2498454 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3360. Min Range: -5.3360
Max Act: 5.0235. Min Act: -0.1700
Data Index: 4962918 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3360. Min Range: -5.3360
Max Act: 5.0547. Min Act: -0.1700
Data Index: 6321844 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3360. Min Range: -5.3360
Max Act: 4.9922. Min Act: -0.1700
Data Index: 877096 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3360. Min Range: -5.3360
Max Act: 4.9922. Min Act: -0.1700
Data Index: 224308 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3360. Min Range: -5.3360
Max Act: 4.9922. Min Act: -0.1700
Data Index: 1576591 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3360. Min Range: -5.3360
Max Act: 4.9610. Min Act: -0.1700
Data Index: 810228 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3360. Min Range: -5.3360
Max Act: 4.9610. Min Act: -0.1700
Data Index: 7862306 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3360. Min Range: -5.3360
Max Act: 4.9297. Min Act: -0.1700
Data Index: 6913453 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3360. Min Range: -5.3360
Max Act: 4.9610. Min Act: -0.1700
Data Index: 1648386 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3360. Min Range: -5.3360
Max Act: 4.9297. Min Act: -0.1700
Data Index: 6726320 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3360. Min Range: -5.3360
Max Act: 4.9297. Min Act: -0.1700
Data Index: 863410 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3360. Min Range: -5.3360
Max Act: 4.8985. Min Act: -0.1700
Data Index: 4863033 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3360. Min Range: -5.3360
Max Act: 4.9297. Min Act: -0.1700
Data Index: 3102081 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3360. Min Range: -5.3360
Max Act: 4.9297. Min Act: -0.1700
Data Index: 1210515 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3360. Min Range: -5.3360
Max Act: 4.9297. Min Act: -0.1700
Data Index: 467968 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3360. Min Range: -5.3360
Max Act: 4.8985. Min Act: -0.1700
Data Index: 2831399 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3360. Min Range: -5.3360
Max Act: 4.8985. Min Act: -0.1700
Data Index: 4109550 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3360. Min Range: -5.3360
Max Act: 4.8985. Min Act: -0.1700
Data Index: 4999711 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19