Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 421 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0307. Min Range: -5.0307
Max Act: 5.0307. Min Act: -0.1700
Data Index: 1418626 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0307. Min Range: -5.0307
Max Act: 5.0307. Min Act: -0.1700
Data Index: 1579835 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0307. Min Range: -5.0307
Max Act: 4.9994. Min Act: -0.1700
Data Index: 8619068 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0307. Min Range: -5.0307
Max Act: 4.9369. Min Act: -0.1700
Data Index: 8404231 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0307. Min Range: -5.0307
Max Act: 4.9369. Min Act: -0.1700
Data Index: 7617166 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0307. Min Range: -5.0307
Max Act: 4.8744. Min Act: -0.1700
Data Index: 5170936 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0307. Min Range: -5.0307
Max Act: 4.7807. Min Act: -0.1700
Data Index: 5707792 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0307. Min Range: -5.0307
Max Act: 4.7807. Min Act: -0.1700
Data Index: 1400333 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0307. Min Range: -5.0307
Max Act: 4.7494. Min Act: -0.1700
Data Index: 844849 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0307. Min Range: -5.0307
Max Act: 4.7494. Min Act: -0.1700
Data Index: 4643777 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0307. Min Range: -5.0307
Max Act: 4.7182. Min Act: -0.1700
Data Index: 736237 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0307. Min Range: -5.0307
Max Act: 4.7494. Min Act: -0.1700
Data Index: 985455 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0307. Min Range: -5.0307
Max Act: 4.7494. Min Act: -0.1700
Data Index: 1495855 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0307. Min Range: -5.0307
Max Act: 4.7182. Min Act: -0.1700
Data Index: 3469166 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0307. Min Range: -5.0307
Max Act: 4.7182. Min Act: -0.1700
Data Index: 3870946 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0307. Min Range: -5.0307
Max Act: 4.7182. Min Act: -0.1700
Data Index: 8279215 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0307. Min Range: -5.0307
Max Act: 4.7182. Min Act: -0.1700
Data Index: 7539650 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0307. Min Range: -5.0307
Max Act: 4.6869. Min Act: -0.1700
Data Index: 2806074 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0307. Min Range: -5.0307
Max Act: 4.6869. Min Act: -0.1700
Data Index: 6418533 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0307. Min Range: -5.0307
Max Act: 4.6557. Min Act: -0.1700
Data Index: 2934412 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19