Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4043 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5672. Min Range: -6.5672
Max Act: 6.5672. Min Act: -0.1700
Data Index: 8181617 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5672. Min Range: -6.5672
Max Act: 6.3172. Min Act: -0.1700
Data Index: 5450232 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5672. Min Range: -6.5672
Max Act: 6.2235. Min Act: -0.1700
Data Index: 3372863 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5672. Min Range: -6.5672
Max Act: 6.1297. Min Act: -0.1700
Data Index: 2305046 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5672. Min Range: -6.5672
Max Act: 6.0672. Min Act: -0.1700
Data Index: 6324288 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5672. Min Range: -6.5672
Max Act: 6.0360. Min Act: -0.1700
Data Index: 5819160 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5672. Min Range: -6.5672
Max Act: 5.9422. Min Act: -0.1700
Data Index: 2851809 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5672. Min Range: -6.5672
Max Act: 5.9422. Min Act: -0.1700
Data Index: 189998 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5672. Min Range: -6.5672
Max Act: 5.9422. Min Act: -0.1700
Data Index: 4223603 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5672. Min Range: -6.5672
Max Act: 5.8485. Min Act: -0.1700
Data Index: 5348561 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5672. Min Range: -6.5672
Max Act: 5.8797. Min Act: -0.1700
Data Index: 2498526 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5672. Min Range: -6.5672
Max Act: 5.8485. Min Act: -0.1700
Data Index: 1241152 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5672. Min Range: -6.5672
Max Act: 5.8485. Min Act: -0.1700
Data Index: 3016366 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5672. Min Range: -6.5672
Max Act: 5.7547. Min Act: -0.1700
Data Index: 1201348 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5672. Min Range: -6.5672
Max Act: 5.7860. Min Act: -0.1699
Data Index: 8703021 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5672. Min Range: -6.5672
Max Act: 5.8172. Min Act: -0.1700
Data Index: 6737770 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5672. Min Range: -6.5672
Max Act: 5.8172. Min Act: -0.1700
Data Index: 6431229 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5672. Min Range: -6.5672
Max Act: 5.7860. Min Act: -0.1700
Data Index: 1883508 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5672. Min Range: -6.5672
Max Act: 5.7547. Min Act: -0.1700
Data Index: 7924329 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5672. Min Range: -6.5672
Max Act: 5.7235. Min Act: -0.1700
Data Index: 681255 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19