Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4396 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9968. Min Range: -3.9968
Max Act: 3.9968. Min Act: -0.1700
Data Index: 4611666 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9968. Min Range: -3.9968
Max Act: 3.9968. Min Act: -0.1700
Data Index: 3687413 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9968. Min Range: -3.9968
Max Act: 3.9655. Min Act: -0.1700
Data Index: 8418788 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9968. Min Range: -3.9968
Max Act: 3.9030. Min Act: -0.1700
Data Index: 2743810 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9968. Min Range: -3.9968
Max Act: 3.9030. Min Act: -0.1700
Data Index: 7088815 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9968. Min Range: -3.9968
Max Act: 3.8717. Min Act: -0.1700
Data Index: 186070 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9968. Min Range: -3.9968
Max Act: 3.8717. Min Act: -0.1700
Data Index: 2743823 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9968. Min Range: -3.9968
Max Act: 3.8717. Min Act: -0.1700
Data Index: 4544955 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9968. Min Range: -3.9968
Max Act: 3.8717. Min Act: -0.1700
Data Index: 6045250 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9968. Min Range: -3.9968
Max Act: 3.8717. Min Act: -0.1700
Data Index: 5469419 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9968. Min Range: -3.9968
Max Act: 3.8717. Min Act: -0.1700
Data Index: 2476420 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9968. Min Range: -3.9968
Max Act: 3.8717. Min Act: -0.1700
Data Index: 8238930 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9968. Min Range: -3.9968
Max Act: 3.8717. Min Act: -0.1700
Data Index: 2822984 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9968. Min Range: -3.9968
Max Act: 3.8404. Min Act: -0.1700
Data Index: 4290983 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9968. Min Range: -3.9968
Max Act: 3.8404. Min Act: -0.1700
Data Index: 5242769 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9968. Min Range: -3.9968
Max Act: 3.8404. Min Act: -0.1700
Data Index: 2562269 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9968. Min Range: -3.9968
Max Act: 3.8404. Min Act: -0.1700
Data Index: 1322320 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9968. Min Range: -3.9968
Max Act: 3.8404. Min Act: -0.1700
Data Index: 4703152 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9968. Min Range: -3.9968
Max Act: 3.8404. Min Act: -0.1700
Data Index: 2149641 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9968. Min Range: -3.9968
Max Act: 3.8404. Min Act: -0.1700
Data Index: 7305976 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19