Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1685 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1280. Min Range: -6.1280
Max Act: 6.1280. Min Act: -0.1700
Data Index: 3134298 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1280. Min Range: -6.1280
Max Act: 6.0030. Min Act: -0.1700
Data Index: 3104382 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1280. Min Range: -6.1280
Max Act: 5.9718. Min Act: -0.1700
Data Index: 5500723 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1280. Min Range: -6.1280
Max Act: 5.9405. Min Act: -0.1700
Data Index: 864350 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1280. Min Range: -6.1280
Max Act: 5.9405. Min Act: -0.1700
Data Index: 2746460 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1280. Min Range: -6.1280
Max Act: 5.9405. Min Act: -0.1700
Data Index: 2269955 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1280. Min Range: -6.1280
Max Act: 5.9093. Min Act: -0.1700
Data Index: 3279785 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1280. Min Range: -6.1280
Max Act: 5.8780. Min Act: -0.1700
Data Index: 4865182 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1280. Min Range: -6.1280
Max Act: 5.8468. Min Act: -0.1700
Data Index: 5571813 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1280. Min Range: -6.1280
Max Act: 5.8155. Min Act: -0.1700
Data Index: 7835734 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1280. Min Range: -6.1280
Max Act: 5.7843. Min Act: -0.1700
Data Index: 4468266 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1280. Min Range: -6.1280
Max Act: 5.7843. Min Act: -0.1700
Data Index: 8420595 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1280. Min Range: -6.1280
Max Act: 5.8155. Min Act: -0.1700
Data Index: 589297 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1280. Min Range: -6.1280
Max Act: 5.7843. Min Act: -0.1700
Data Index: 267005 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1280. Min Range: -6.1280
Max Act: 5.7843. Min Act: -0.1700
Data Index: 3874179 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1280. Min Range: -6.1280
Max Act: 5.7530. Min Act: -0.1700
Data Index: 6154063 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1280. Min Range: -6.1280
Max Act: 5.7218. Min Act: -0.1700
Data Index: 8773171 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1280. Min Range: -6.1280
Max Act: 5.7530. Min Act: -0.1700
Data Index: 2738765 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1280. Min Range: -6.1280
Max Act: 5.7530. Min Act: -0.1700
Data Index: 6974091 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1280. Min Range: -6.1280
Max Act: 5.7218. Min Act: -0.1700
Data Index: 3325389 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19