Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2927 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4127. Min Range: -6.4127
Max Act: 6.4127. Min Act: -0.1700
Data Index: 1209425 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4127. Min Range: -6.4127
Max Act: 6.3815. Min Act: -0.1700
Data Index: 3152622 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4127. Min Range: -6.4127
Max Act: 6.3502. Min Act: -0.1700
Data Index: 6249963 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4127. Min Range: -6.4127
Max Act: 6.3502. Min Act: -0.1700
Data Index: 5330433 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4127. Min Range: -6.4127
Max Act: 6.2877. Min Act: -0.1700
Data Index: 6030302 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4127. Min Range: -6.4127
Max Act: 6.2877. Min Act: -0.1700
Data Index: 5063793 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4127. Min Range: -6.4127
Max Act: 6.2877. Min Act: -0.1700
Data Index: 3688857 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4127. Min Range: -6.4127
Max Act: 6.2565. Min Act: -0.1700
Data Index: 7719861 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4127. Min Range: -6.4127
Max Act: 6.2252. Min Act: -0.1700
Data Index: 4848321 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4127. Min Range: -6.4127
Max Act: 6.2252. Min Act: -0.1700
Data Index: 78632 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4127. Min Range: -6.4127
Max Act: 6.1940. Min Act: -0.1700
Data Index: 7435571 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4127. Min Range: -6.4127
Max Act: 6.1940. Min Act: -0.1700
Data Index: 5376599 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4127. Min Range: -6.4127
Max Act: 6.2252. Min Act: -0.1700
Data Index: 7324230 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4127. Min Range: -6.4127
Max Act: 6.1940. Min Act: -0.1698
Data Index: 6330408 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4127. Min Range: -6.4127
Max Act: 6.1940. Min Act: -0.1700
Data Index: 3319367 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4127. Min Range: -6.4127
Max Act: 6.1940. Min Act: -0.1700
Data Index: 1877421 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4127. Min Range: -6.4127
Max Act: 6.1940. Min Act: -0.1700
Data Index: 4228291 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4127. Min Range: -6.4127
Max Act: 6.1627. Min Act: -0.1700
Data Index: 3806094 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4127. Min Range: -6.4127
Max Act: 6.1627. Min Act: -0.1700
Data Index: 3909553 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4127. Min Range: -6.4127
Max Act: 6.1627. Min Act: -0.1700
Data Index: 581490 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19