Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4330 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8273. Min Range: -4.8273
Max Act: 4.8273. Min Act: -0.1700
Data Index: 6142400 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8273. Min Range: -4.8273
Max Act: 4.5773. Min Act: -0.1700
Data Index: 5322306 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8273. Min Range: -4.8273
Max Act: 4.6086. Min Act: -0.1700
Data Index: 7803095 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8273. Min Range: -4.8273
Max Act: 4.5773. Min Act: -0.1700
Data Index: 1411274 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8273. Min Range: -4.8273
Max Act: 4.5773. Min Act: -0.1700
Data Index: 2372427 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8273. Min Range: -4.8273
Max Act: 4.5461. Min Act: -0.1700
Data Index: 2253288 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8273. Min Range: -4.8273
Max Act: 4.5148. Min Act: -0.1700
Data Index: 7894718 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8273. Min Range: -4.8273
Max Act: 4.4836. Min Act: -0.1700
Data Index: 6332914 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8273. Min Range: -4.8273
Max Act: 4.4836. Min Act: -0.1700
Data Index: 8484732 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8273. Min Range: -4.8273
Max Act: 4.4211. Min Act: -0.1700
Data Index: 1975225 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8273. Min Range: -4.8273
Max Act: 4.4211. Min Act: -0.1700
Data Index: 5322312 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8273. Min Range: -4.8273
Max Act: 4.3898. Min Act: -0.1700
Data Index: 4906619 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8273. Min Range: -4.8273
Max Act: 4.4211. Min Act: -0.1700
Data Index: 5973490 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8273. Min Range: -4.8273
Max Act: 4.3273. Min Act: -0.1700
Data Index: 5450927 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8273. Min Range: -4.8273
Max Act: 4.3273. Min Act: -0.1700
Data Index: 4491747 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8273. Min Range: -4.8273
Max Act: 4.2961. Min Act: -0.1700
Data Index: 8426790 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8273. Min Range: -4.8273
Max Act: 4.2961. Min Act: -0.1700
Data Index: 8520928 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8273. Min Range: -4.8273
Max Act: 4.2961. Min Act: -0.1700
Data Index: 1280942 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8273. Min Range: -4.8273
Max Act: 4.2648. Min Act: -0.1700
Data Index: 4957764 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8273. Min Range: -4.8273
Max Act: 4.2648. Min Act: -0.1700
Data Index: 8002100 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19