Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4904 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6530. Min Range: -5.6530
Max Act: 5.6530. Min Act: -0.1700
Data Index: 5355159 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6530. Min Range: -5.6530
Max Act: 5.4655. Min Act: -0.1700
Data Index: 1442220 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6530. Min Range: -5.6530
Max Act: 5.4343. Min Act: -0.1700
Data Index: 4209542 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6530. Min Range: -5.6530
Max Act: 5.4030. Min Act: -0.1700
Data Index: 4711132 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6530. Min Range: -5.6530
Max Act: 5.3405. Min Act: -0.1700
Data Index: 545236 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6530. Min Range: -5.6530
Max Act: 5.3093. Min Act: -0.1700
Data Index: 2638883 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6530. Min Range: -5.6530
Max Act: 5.2780. Min Act: -0.1700
Data Index: 8128411 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6530. Min Range: -5.6530
Max Act: 5.2780. Min Act: -0.1700
Data Index: 8149289 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6530. Min Range: -5.6530
Max Act: 5.2780. Min Act: -0.1700
Data Index: 7375096 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6530. Min Range: -5.6530
Max Act: 5.2780. Min Act: -0.1700
Data Index: 3660059 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6530. Min Range: -5.6530
Max Act: 5.2780. Min Act: -0.1700
Data Index: 7284335 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6530. Min Range: -5.6530
Max Act: 5.2468. Min Act: -0.1700
Data Index: 2306558 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6530. Min Range: -5.6530
Max Act: 5.2468. Min Act: -0.1700
Data Index: 1105546 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6530. Min Range: -5.6530
Max Act: 5.2468. Min Act: -0.1700
Data Index: 2640129 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6530. Min Range: -5.6530
Max Act: 5.2468. Min Act: -0.1700
Data Index: 4820612 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6530. Min Range: -5.6530
Max Act: 5.2468. Min Act: -0.1700
Data Index: 6848238 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6530. Min Range: -5.6530
Max Act: 5.2468. Min Act: -0.1700
Data Index: 7224921 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6530. Min Range: -5.6530
Max Act: 5.2468. Min Act: -0.1700
Data Index: 7167361 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6530. Min Range: -5.6530
Max Act: 5.2155. Min Act: -0.1700
Data Index: 4379299 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6530. Min Range: -5.6530
Max Act: 5.2155. Min Act: -0.1700
Data Index: 1921220 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19