Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 34 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4081. Min Range: -5.4081
Max Act: 5.4081. Min Act: -0.1700
Data Index: 4073572 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4081. Min Range: -5.4081
Max Act: 5.3456. Min Act: -0.1700
Data Index: 5906060 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4081. Min Range: -5.4081
Max Act: 5.2518. Min Act: -0.1700
Data Index: 1148202 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4081. Min Range: -5.4081
Max Act: 5.2518. Min Act: -0.1700
Data Index: 3312264 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4081. Min Range: -5.4081
Max Act: 5.2518. Min Act: -0.1700
Data Index: 8755687 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4081. Min Range: -5.4081
Max Act: 5.2518. Min Act: -0.1700
Data Index: 1932364 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4081. Min Range: -5.4081
Max Act: 5.2206. Min Act: -0.1700
Data Index: 34228 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4081. Min Range: -5.4081
Max Act: 5.2206. Min Act: -0.1700
Data Index: 6488907 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4081. Min Range: -5.4081
Max Act: 5.2206. Min Act: -0.1700
Data Index: 6052310 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4081. Min Range: -5.4081
Max Act: 5.2206. Min Act: -0.1700
Data Index: 5770009 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4081. Min Range: -5.4081
Max Act: 5.2206. Min Act: -0.1700
Data Index: 2233156 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4081. Min Range: -5.4081
Max Act: 5.2206. Min Act: -0.1700
Data Index: 1698554 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4081. Min Range: -5.4081
Max Act: 5.2206. Min Act: -0.1700
Data Index: 937262 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4081. Min Range: -5.4081
Max Act: 5.2206. Min Act: -0.1700
Data Index: 8628844 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4081. Min Range: -5.4081
Max Act: 5.2206. Min Act: -0.1700
Data Index: 3386926 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4081. Min Range: -5.4081
Max Act: 5.1893. Min Act: -0.1700
Data Index: 7433885 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4081. Min Range: -5.4081
Max Act: 5.1893. Min Act: -0.1700
Data Index: 6855883 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4081. Min Range: -5.4081
Max Act: 5.1893. Min Act: -0.1700
Data Index: 3871874 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4081. Min Range: -5.4081
Max Act: 5.2206. Min Act: -0.1700
Data Index: 3466073 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4081. Min Range: -5.4081
Max Act: 5.1581. Min Act: -0.1700
Data Index: 891101 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19