Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 291 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5145. Min Range: -5.5145
Max Act: 5.5145. Min Act: -0.1700
Data Index: 6630623 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5145. Min Range: -5.5145
Max Act: 5.4207. Min Act: -0.1700
Data Index: 7579168 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5145. Min Range: -5.5145
Max Act: 5.3582. Min Act: -0.1700
Data Index: 5892146 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5145. Min Range: -5.5145
Max Act: 5.2957. Min Act: -0.1700
Data Index: 7971382 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5145. Min Range: -5.5145
Max Act: 5.2645. Min Act: -0.1700
Data Index: 1447627 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5145. Min Range: -5.5145
Max Act: 5.2332. Min Act: -0.1699
Data Index: 3156576 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5145. Min Range: -5.5145
Max Act: 5.2020. Min Act: -0.1700
Data Index: 5463135 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5145. Min Range: -5.5145
Max Act: 5.2020. Min Act: -0.1700
Data Index: 2146058 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5145. Min Range: -5.5145
Max Act: 5.2020. Min Act: -0.1700
Data Index: 1745076 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5145. Min Range: -5.5145
Max Act: 5.2020. Min Act: -0.1700
Data Index: 3163461 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5145. Min Range: -5.5145
Max Act: 5.1707. Min Act: -0.1700
Data Index: 3793461 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5145. Min Range: -5.5145
Max Act: 5.1707. Min Act: -0.1697
Data Index: 1108353 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5145. Min Range: -5.5145
Max Act: 5.1707. Min Act: -0.1700
Data Index: 817553 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5145. Min Range: -5.5145
Max Act: 5.1707. Min Act: -0.1700
Data Index: 711042 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5145. Min Range: -5.5145
Max Act: 5.1707. Min Act: -0.1700
Data Index: 2196429 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5145. Min Range: -5.5145
Max Act: 5.1082. Min Act: -0.1700
Data Index: 950210 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5145. Min Range: -5.5145
Max Act: 5.1395. Min Act: -0.1700
Data Index: 3346098 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5145. Min Range: -5.5145
Max Act: 5.1395. Min Act: -0.1700
Data Index: 6381391 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5145. Min Range: -5.5145
Max Act: 5.1707. Min Act: -0.1700
Data Index: 5358280 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5145. Min Range: -5.5145
Max Act: 5.1395. Min Act: -0.1700
Data Index: 6190535 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19