Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5303 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1214. Min Range: -6.1214
Max Act: 6.1214. Min Act: -0.1700
Data Index: 7623486 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1214. Min Range: -6.1214
Max Act: 6.0277. Min Act: -0.1700
Data Index: 4965117 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1214. Min Range: -6.1214
Max Act: 5.9652. Min Act: -0.1700
Data Index: 4856912 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1214. Min Range: -6.1214
Max Act: 5.9652. Min Act: -0.1700
Data Index: 6641141 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1214. Min Range: -6.1214
Max Act: 5.9339. Min Act: -0.1700
Data Index: 787907 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1214. Min Range: -6.1214
Max Act: 5.9027. Min Act: -0.1700
Data Index: 6854124 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1214. Min Range: -6.1214
Max Act: 5.9027. Min Act: -0.1700
Data Index: 7767321 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1214. Min Range: -6.1214
Max Act: 5.9027. Min Act: -0.1700
Data Index: 6468766 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1214. Min Range: -6.1214
Max Act: 5.8714. Min Act: -0.1700
Data Index: 5053213 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1214. Min Range: -6.1214
Max Act: 5.8714. Min Act: -0.1700
Data Index: 1362248 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1214. Min Range: -6.1214
Max Act: 5.8402. Min Act: -0.1700
Data Index: 6426286 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1214. Min Range: -6.1214
Max Act: 5.9027. Min Act: -0.1700
Data Index: 3459925 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1214. Min Range: -6.1214
Max Act: 5.8714. Min Act: -0.1700
Data Index: 5116700 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1214. Min Range: -6.1214
Max Act: 5.8402. Min Act: -0.1700
Data Index: 5624454 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1214. Min Range: -6.1214
Max Act: 5.8089. Min Act: -0.1700
Data Index: 3865110 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1214. Min Range: -6.1214
Max Act: 5.7777. Min Act: -0.1700
Data Index: 2891868 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1214. Min Range: -6.1214
Max Act: 5.7777. Min Act: -0.1700
Data Index: 5498291 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1214. Min Range: -6.1214
Max Act: 5.7777. Min Act: -0.1700
Data Index: 1086329 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1214. Min Range: -6.1214
Max Act: 5.7777. Min Act: -0.1700
Data Index: 2367339 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1214. Min Range: -6.1214
Max Act: 5.7777. Min Act: -0.1700
Data Index: 1347073 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #19