Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1112 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.4276. Min Act: -0.1700
Data Index: 342354 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.4276. Min Act: -0.1700
Data Index: 530732 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.2713. Min Act: -0.1700
Data Index: 638623 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.2713. Min Act: -0.1700
Data Index: 5822753 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.2401. Min Act: -0.1700
Data Index: 992182 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.2401. Min Act: -0.1700
Data Index: 5029712 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.2401. Min Act: -0.1700
Data Index: 1265797 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.2088. Min Act: -0.1700
Data Index: 2951390 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.1776. Min Act: -0.1700
Data Index: 8785053 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.1463. Min Act: -0.1700
Data Index: 1792077 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.1463. Min Act: -0.1700
Data Index: 6927292 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.1463. Min Act: -0.1700
Data Index: 6125759 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.1151. Min Act: -0.1700
Data Index: 7073223 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.1151. Min Act: -0.1700
Data Index: 2097674 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.1151. Min Act: -0.1700
Data Index: 5826774 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.0838. Min Act: -0.1700
Data Index: 516394 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.0838. Min Act: -0.1700
Data Index: 4641333 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.0838. Min Act: -0.1700
Data Index: 4037301 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.0526. Min Act: -0.1700
Data Index: 215638 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4276. Min Range: -5.4276
Max Act: 5.0213. Min Act: -0.1700
Data Index: 270327 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19