Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6166 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3221. Min Range: -3.3221
Max Act: 3.3221. Min Act: -0.1700
Data Index: 8043267 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3221. Min Range: -3.3221
Max Act: 3.3064. Min Act: -0.1700
Data Index: 6193002 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3221. Min Range: -3.3221
Max Act: 3.2907. Min Act: -0.1700
Data Index: 2454809 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3221. Min Range: -3.3221
Max Act: 3.2593. Min Act: -0.1700
Data Index: 3485962 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3221. Min Range: -3.3221
Max Act: 3.2593. Min Act: -0.1700
Data Index: 1782478 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3221. Min Range: -3.3221
Max Act: 3.2121. Min Act: -0.1700
Data Index: 4876340 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3221. Min Range: -3.3221
Max Act: 3.2121. Min Act: -0.1700
Data Index: 7947160 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3221. Min Range: -3.3221
Max Act: 3.2121. Min Act: -0.1700
Data Index: 556840 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3221. Min Range: -3.3221
Max Act: 3.1807. Min Act: -0.1700
Data Index: 2930358 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3221. Min Range: -3.3221
Max Act: 3.1649. Min Act: -0.1700
Data Index: 8043274 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3221. Min Range: -3.3221
Max Act: 3.1177. Min Act: -0.1700
Data Index: 974293 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3221. Min Range: -3.3221
Max Act: 3.1177. Min Act: -0.1700
Data Index: 1746955 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3221. Min Range: -3.3221
Max Act: 3.1177. Min Act: -0.1700
Data Index: 466704 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3221. Min Range: -3.3221
Max Act: 3.1177. Min Act: -0.1700
Data Index: 1319719 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3221. Min Range: -3.3221
Max Act: 3.1177. Min Act: -0.1700
Data Index: 1326943 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3221. Min Range: -3.3221
Max Act: 3.1177. Min Act: -0.1700
Data Index: 1497344 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3221. Min Range: -3.3221
Max Act: 3.1177. Min Act: -0.1700
Data Index: 1957210 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3221. Min Range: -3.3221
Max Act: 3.1177. Min Act: -0.1700
Data Index: 1462906 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3221. Min Range: -3.3221
Max Act: 3.1177. Min Act: -0.1700
Data Index: 205240 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3221. Min Range: -3.3221
Max Act: 3.1177. Min Act: -0.1700
Data Index: 585385 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19