Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3352 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.5448. Min Act: -0.1700
Data Index: 2377601 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.4511. Min Act: -0.1700
Data Index: 8127304 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.3886. Min Act: -0.1700
Data Index: 3300024 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.3886. Min Act: -0.1700
Data Index: 6798436 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.3573. Min Act: -0.1700
Data Index: 8009445 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.3261. Min Act: -0.1700
Data Index: 4227162 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.2636. Min Act: -0.1700
Data Index: 8433480 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.2636. Min Act: -0.1700
Data Index: 2541676 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.2636. Min Act: -0.1700
Data Index: 176361 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.2323. Min Act: -0.1700
Data Index: 4371617 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.1698. Min Act: -0.1700
Data Index: 6355180 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.1698. Min Act: -0.1700
Data Index: 7503849 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.1698. Min Act: -0.1700
Data Index: 6355181 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.1386. Min Act: -0.1700
Data Index: 3547098 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.1386. Min Act: -0.1700
Data Index: 3547099 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.1698. Min Act: -0.1700
Data Index: 1295683 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.1073. Min Act: -0.1700
Data Index: 8374985 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.1073. Min Act: -0.1700
Data Index: 2974393 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.1073. Min Act: -0.1700
Data Index: 5136179 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5448. Min Range: -5.5448
Max Act: 5.0761. Min Act: -0.1700
Data Index: 5617754 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19