Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3319 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6542. Min Range: -6.6542
Max Act: 6.6542. Min Act: -0.1700
Data Index: 8722025 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6542. Min Range: -6.6542
Max Act: 6.5917. Min Act: -0.1700
Data Index: 8121879 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6542. Min Range: -6.6542
Max Act: 6.4667. Min Act: -0.1700
Data Index: 5893203 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6542. Min Range: -6.6542
Max Act: 6.4042. Min Act: -0.1700
Data Index: 2091473 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6542. Min Range: -6.6542
Max Act: 6.3417. Min Act: -0.1700
Data Index: 5262313 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6542. Min Range: -6.6542
Max Act: 6.3417. Min Act: -0.1700
Data Index: 8787290 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6542. Min Range: -6.6542
Max Act: 6.3729. Min Act: -0.1700
Data Index: 6581278 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6542. Min Range: -6.6542
Max Act: 6.3729. Min Act: -0.1700
Data Index: 8344902 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6542. Min Range: -6.6542
Max Act: 6.3417. Min Act: -0.1700
Data Index: 3272389 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6542. Min Range: -6.6542
Max Act: 6.3104. Min Act: -0.1700
Data Index: 3682952 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6542. Min Range: -6.6542
Max Act: 6.2792. Min Act: -0.1700
Data Index: 8265703 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6542. Min Range: -6.6542
Max Act: 6.2479. Min Act: -0.1700
Data Index: 1676373 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6542. Min Range: -6.6542
Max Act: 6.2479. Min Act: -0.1700
Data Index: 3563941 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6542. Min Range: -6.6542
Max Act: 6.2167. Min Act: -0.1700
Data Index: 1513246 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6542. Min Range: -6.6542
Max Act: 6.1854. Min Act: -0.1700
Data Index: 3044215 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6542. Min Range: -6.6542
Max Act: 6.1542. Min Act: -0.1700
Data Index: 4507439 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6542. Min Range: -6.6542
Max Act: 6.1542. Min Act: -0.1700
Data Index: 5028754 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6542. Min Range: -6.6542
Max Act: 6.1229. Min Act: -0.1700
Data Index: 6697710 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6542. Min Range: -6.6542
Max Act: 6.1229. Min Act: -0.1700
Data Index: 8406683 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6542. Min Range: -6.6542
Max Act: 6.1229. Min Act: -0.1700
Data Index: 4065621 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19