Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4089 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.3542. Min Range: -7.3542
Max Act: 7.3542. Min Act: -0.1700
Data Index: 7076618 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3542. Min Range: -7.3542
Max Act: 7.2917. Min Act: -0.1700
Data Index: 4971717 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3542. Min Range: -7.3542
Max Act: 7.2604. Min Act: -0.1700
Data Index: 7699099 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3542. Min Range: -7.3542
Max Act: 7.2292. Min Act: -0.1700
Data Index: 106258 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3542. Min Range: -7.3542
Max Act: 7.1354. Min Act: -0.1700
Data Index: 4330734 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3542. Min Range: -7.3542
Max Act: 7.1354. Min Act: -0.1700
Data Index: 4140477 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3542. Min Range: -7.3542
Max Act: 7.1354. Min Act: -0.1700
Data Index: 4144136 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3542. Min Range: -7.3542
Max Act: 7.1042. Min Act: -0.1700
Data Index: 3677133 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3542. Min Range: -7.3542
Max Act: 7.1042. Min Act: -0.1700
Data Index: 5116276 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3542. Min Range: -7.3542
Max Act: 7.0417. Min Act: -0.1700
Data Index: 3858864 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3542. Min Range: -7.3542
Max Act: 7.0104. Min Act: -0.1700
Data Index: 4944857 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3542. Min Range: -7.3542
Max Act: 6.9792. Min Act: -0.1700
Data Index: 4169925 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3542. Min Range: -7.3542
Max Act: 6.9479. Min Act: -0.1700
Data Index: 530247 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3542. Min Range: -7.3542
Max Act: 6.9479. Min Act: -0.1700
Data Index: 472344 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3542. Min Range: -7.3542
Max Act: 6.9167. Min Act: -0.1700
Data Index: 6410647 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3542. Min Range: -7.3542
Max Act: 6.8542. Min Act: -0.1700
Data Index: 4137916 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3542. Min Range: -7.3542
Max Act: 6.8542. Min Act: -0.1700
Data Index: 2929681 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3542. Min Range: -7.3542
Max Act: 6.8229. Min Act: -0.1700
Data Index: 6376997 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3542. Min Range: -7.3542
Max Act: 6.8229. Min Act: -0.1700
Data Index: 733971 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3542. Min Range: -7.3542
Max Act: 6.8542. Min Act: -0.1700
Data Index: 1500379 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #19