Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2703 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6688. Min Range: -5.6688
Max Act: 5.6688. Min Act: -0.1700
Data Index: 6138411 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6688. Min Range: -5.6688
Max Act: 5.6375. Min Act: -0.1700
Data Index: 6495294 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6688. Min Range: -5.6688
Max Act: 5.6063. Min Act: -0.1700
Data Index: 5533045 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6688. Min Range: -5.6688
Max Act: 5.5750. Min Act: -0.1700
Data Index: 4866236 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6688. Min Range: -5.6688
Max Act: 5.6063. Min Act: -0.1700
Data Index: 2839535 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6688. Min Range: -5.6688
Max Act: 5.6063. Min Act: -0.1700
Data Index: 8382327 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6688. Min Range: -5.6688
Max Act: 5.6063. Min Act: -0.1700
Data Index: 7170869 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6688. Min Range: -5.6688
Max Act: 5.6063. Min Act: -0.1700
Data Index: 3079372 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6688. Min Range: -5.6688
Max Act: 5.5750. Min Act: -0.1700
Data Index: 1013624 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6688. Min Range: -5.6688
Max Act: 5.5750. Min Act: -0.1700
Data Index: 583055 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6688. Min Range: -5.6688
Max Act: 5.5438. Min Act: -0.1700
Data Index: 666369 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6688. Min Range: -5.6688
Max Act: 5.5125. Min Act: -0.1700
Data Index: 3880465 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6688. Min Range: -5.6688
Max Act: 5.4813. Min Act: -0.1700
Data Index: 1108507 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6688. Min Range: -5.6688
Max Act: 5.4813. Min Act: -0.1700
Data Index: 6855421 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6688. Min Range: -5.6688
Max Act: 5.4813. Min Act: -0.1700
Data Index: 3662397 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6688. Min Range: -5.6688
Max Act: 5.5125. Min Act: -0.1700
Data Index: 42791 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6688. Min Range: -5.6688
Max Act: 5.4813. Min Act: -0.1700
Data Index: 7861291 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6688. Min Range: -5.6688
Max Act: 5.4500. Min Act: -0.1700
Data Index: 638739 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6688. Min Range: -5.6688
Max Act: 5.4813. Min Act: -0.1700
Data Index: 4055196 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6688. Min Range: -5.6688
Max Act: 5.4500. Min Act: -0.1700
Data Index: 2985279 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19