Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5333 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9153. Min Range: -6.9153
Max Act: 6.9153. Min Act: -0.1700
Data Index: 154287 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9153. Min Range: -6.9153
Max Act: 6.6028. Min Act: -0.1700
Data Index: 6109126 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9153. Min Range: -6.9153
Max Act: 6.5090. Min Act: -0.1700
Data Index: 8067248 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9153. Min Range: -6.9153
Max Act: 6.5090. Min Act: -0.1700
Data Index: 8818437 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9153. Min Range: -6.9153
Max Act: 6.2590. Min Act: -0.1700
Data Index: 2961682 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9153. Min Range: -6.9153
Max Act: 6.2278. Min Act: -0.1700
Data Index: 3396628 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9153. Min Range: -6.9153
Max Act: 6.1965. Min Act: -0.1700
Data Index: 2962482 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9153. Min Range: -6.9153
Max Act: 6.1340. Min Act: -0.1700
Data Index: 5090181 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9153. Min Range: -6.9153
Max Act: 6.1653. Min Act: -0.1700
Data Index: 2934477 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9153. Min Range: -6.9153
Max Act: 6.1028. Min Act: -0.1700
Data Index: 3980033 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9153. Min Range: -6.9153
Max Act: 6.0715. Min Act: -0.1700
Data Index: 3852367 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9153. Min Range: -6.9153
Max Act: 6.0715. Min Act: -0.1700
Data Index: 3322309 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9153. Min Range: -6.9153
Max Act: 6.0715. Min Act: -0.1700
Data Index: 4928559 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9153. Min Range: -6.9153
Max Act: 6.0403. Min Act: -0.1700
Data Index: 5204647 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9153. Min Range: -6.9153
Max Act: 6.0090. Min Act: -0.1700
Data Index: 1891552 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9153. Min Range: -6.9153
Max Act: 6.0090. Min Act: -0.1700
Data Index: 7092049 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9153. Min Range: -6.9153
Max Act: 5.9778. Min Act: -0.1700
Data Index: 2599726 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9153. Min Range: -6.9153
Max Act: 5.9778. Min Act: -0.1700
Data Index: 8431081 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9153. Min Range: -6.9153
Max Act: 5.9778. Min Act: -0.1700
Data Index: 6991271 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9153. Min Range: -6.9153
Max Act: 5.9153. Min Act: -0.1700
Data Index: 2065871 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19