Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4843 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4131. Min Range: -4.4131
Max Act: 4.4131. Min Act: -0.1700
Data Index: 6681005 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4131. Min Range: -4.4131
Max Act: 4.3193. Min Act: -0.1700
Data Index: 5068799 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4131. Min Range: -4.4131
Max Act: 4.2881. Min Act: -0.1700
Data Index: 8634292 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4131. Min Range: -4.4131
Max Act: 4.2881. Min Act: -0.1700
Data Index: 8242958 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4131. Min Range: -4.4131
Max Act: 4.2881. Min Act: -0.1700
Data Index: 6575112 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4131. Min Range: -4.4131
Max Act: 4.2568. Min Act: -0.1700
Data Index: 2980666 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4131. Min Range: -4.4131
Max Act: 4.2568. Min Act: -0.1700
Data Index: 1048306 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4131. Min Range: -4.4131
Max Act: 4.2568. Min Act: -0.1700
Data Index: 5316137 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4131. Min Range: -4.4131
Max Act: 4.2568. Min Act: -0.1700
Data Index: 5143445 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4131. Min Range: -4.4131
Max Act: 4.2256. Min Act: -0.1700
Data Index: 1301567 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4131. Min Range: -4.4131
Max Act: 4.2256. Min Act: -0.1700
Data Index: 7997432 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4131. Min Range: -4.4131
Max Act: 4.1943. Min Act: -0.1700
Data Index: 6591607 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4131. Min Range: -4.4131
Max Act: 4.1943. Min Act: -0.1700
Data Index: 8036051 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4131. Min Range: -4.4131
Max Act: 4.1943. Min Act: -0.1700
Data Index: 6923279 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4131. Min Range: -4.4131
Max Act: 4.1943. Min Act: -0.1700
Data Index: 4622668 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4131. Min Range: -4.4131
Max Act: 4.1631. Min Act: -0.1700
Data Index: 1669917 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4131. Min Range: -4.4131
Max Act: 4.1631. Min Act: -0.1700
Data Index: 7935658 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4131. Min Range: -4.4131
Max Act: 4.1631. Min Act: -0.1700
Data Index: 4241811 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4131. Min Range: -4.4131
Max Act: 4.1631. Min Act: -0.1700
Data Index: 2562238 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4131. Min Range: -4.4131
Max Act: 4.1631. Min Act: -0.1700
Data Index: 4856432 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19