Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2114 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.3991. Min Range: -1.3991
Max Act: 1.3991. Min Act: -0.1700
Data Index: 5993983 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3991. Min Range: -1.3991
Max Act: 1.3814. Min Act: -0.1700
Data Index: 5798664 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3991. Min Range: -1.3991
Max Act: 1.3638. Min Act: -0.1700
Data Index: 808055 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3991. Min Range: -1.3991
Max Act: 1.3285. Min Act: -0.1700
Data Index: 4304633 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3991. Min Range: -1.3991
Max Act: 1.2932. Min Act: -0.1700
Data Index: 5005910 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3991. Min Range: -1.3991
Max Act: 1.3109. Min Act: -0.1700
Data Index: 2495338 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3991. Min Range: -1.3991
Max Act: 1.3109. Min Act: -0.1699
Data Index: 7062713 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3991. Min Range: -1.3991
Max Act: 1.3109. Min Act: -0.1700
Data Index: 2203399 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3991. Min Range: -1.3991
Max Act: 1.3109. Min Act: -0.1700
Data Index: 8116316 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3991. Min Range: -1.3991
Max Act: 1.2932. Min Act: -0.1700
Data Index: 5800591 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3991. Min Range: -1.3991
Max Act: 1.2932. Min Act: -0.1700
Data Index: 1779243 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3991. Min Range: -1.3991
Max Act: 1.2932. Min Act: -0.1700
Data Index: 6348042 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3991. Min Range: -1.3991
Max Act: 1.2932. Min Act: -0.1700
Data Index: 5291325 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3991. Min Range: -1.3991
Max Act: 1.2932. Min Act: -0.1699
Data Index: 7801723 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3991. Min Range: -1.3991
Max Act: 1.2932. Min Act: -0.1700
Data Index: 3759816 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3991. Min Range: -1.3991
Max Act: 1.2756. Min Act: -0.1700
Data Index: 1405077 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3991. Min Range: -1.3991
Max Act: 1.2756. Min Act: -0.1700
Data Index: 6720513 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3991. Min Range: -1.3991
Max Act: 1.2756. Min Act: -0.1700
Data Index: 303935 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3991. Min Range: -1.3991
Max Act: 1.2580. Min Act: -0.1700
Data Index: 6194375 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3991. Min Range: -1.3991
Max Act: 1.2580. Min Act: -0.1700
Data Index: 960970 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19