Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2589 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4279. Min Range: -6.4279
Max Act: 6.4279. Min Act: -0.1700
Data Index: 3709566 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4279. Min Range: -6.4279
Max Act: 5.8654. Min Act: -0.1700
Data Index: 6082385 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4279. Min Range: -6.4279
Max Act: 5.8342. Min Act: -0.1700
Data Index: 8491842 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4279. Min Range: -6.4279
Max Act: 5.8342. Min Act: -0.1700
Data Index: 3337778 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4279. Min Range: -6.4279
Max Act: 5.7092. Min Act: -0.1700
Data Index: 8574126 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4279. Min Range: -6.4279
Max Act: 5.7404. Min Act: -0.1700
Data Index: 3852720 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4279. Min Range: -6.4279
Max Act: 5.7092. Min Act: -0.1700
Data Index: 165867 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4279. Min Range: -6.4279
Max Act: 5.7092. Min Act: -0.1700
Data Index: 1524330 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4279. Min Range: -6.4279
Max Act: 5.6779. Min Act: -0.1700
Data Index: 5185106 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4279. Min Range: -6.4279
Max Act: 5.6779. Min Act: -0.1700
Data Index: 6108592 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4279. Min Range: -6.4279
Max Act: 5.6467. Min Act: -0.1700
Data Index: 5237349 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4279. Min Range: -6.4279
Max Act: 5.6467. Min Act: -0.1700
Data Index: 5416094 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4279. Min Range: -6.4279
Max Act: 5.6467. Min Act: -0.1700
Data Index: 555293 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4279. Min Range: -6.4279
Max Act: 5.6467. Min Act: -0.1700
Data Index: 6883341 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4279. Min Range: -6.4279
Max Act: 5.5842. Min Act: -0.1700
Data Index: 35956 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4279. Min Range: -6.4279
Max Act: 5.6154. Min Act: -0.1700
Data Index: 2118278 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4279. Min Range: -6.4279
Max Act: 5.6154. Min Act: -0.1700
Data Index: 2877539 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4279. Min Range: -6.4279
Max Act: 5.5529. Min Act: -0.1700
Data Index: 187611 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4279. Min Range: -6.4279
Max Act: 5.5842. Min Act: -0.1700
Data Index: 4960276 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4279. Min Range: -6.4279
Max Act: 5.5842. Min Act: -0.1700
Data Index: 5391443 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #19