Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3566 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7116. Min Range: -4.7116
Max Act: 4.7116. Min Act: -0.1700
Data Index: 8610785 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7116. Min Range: -4.7116
Max Act: 4.6804. Min Act: -0.1700
Data Index: 8285752 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7116. Min Range: -4.7116
Max Act: 4.6179. Min Act: -0.1700
Data Index: 1616308 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7116. Min Range: -4.7116
Max Act: 4.5554. Min Act: -0.1700
Data Index: 1440032 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7116. Min Range: -4.7116
Max Act: 4.5866. Min Act: -0.1700
Data Index: 8782400 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7116. Min Range: -4.7116
Max Act: 4.5241. Min Act: -0.1700
Data Index: 6629702 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7116. Min Range: -4.7116
Max Act: 4.5241. Min Act: -0.1700
Data Index: 6136159 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7116. Min Range: -4.7116
Max Act: 4.4929. Min Act: -0.1700
Data Index: 6175020 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7116. Min Range: -4.7116
Max Act: 4.4929. Min Act: -0.1700
Data Index: 7807168 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7116. Min Range: -4.7116
Max Act: 4.5241. Min Act: -0.1700
Data Index: 7217289 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7116. Min Range: -4.7116
Max Act: 4.4929. Min Act: -0.1700
Data Index: 2330506 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7116. Min Range: -4.7116
Max Act: 4.4616. Min Act: -0.1700
Data Index: 1185492 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7116. Min Range: -4.7116
Max Act: 4.4616. Min Act: -0.1700
Data Index: 6917582 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7116. Min Range: -4.7116
Max Act: 4.4616. Min Act: -0.1700
Data Index: 5140774 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7116. Min Range: -4.7116
Max Act: 4.4616. Min Act: -0.1700
Data Index: 4438780 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7116. Min Range: -4.7116
Max Act: 4.4304. Min Act: -0.1700
Data Index: 3457685 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7116. Min Range: -4.7116
Max Act: 4.4304. Min Act: -0.1700
Data Index: 1623691 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7116. Min Range: -4.7116
Max Act: 4.3991. Min Act: -0.1700
Data Index: 1163810 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7116. Min Range: -4.7116
Max Act: 4.3991. Min Act: -0.1700
Data Index: 7820256 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7116. Min Range: -4.7116
Max Act: 4.3991. Min Act: -0.1700
Data Index: 6113089 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #19