Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 179 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.5089. Min Act: -0.1700
Data Index: 7042418 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.5402. Min Act: -0.1700
Data Index: 7042417 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.4777. Min Act: -0.1700
Data Index: 4397175 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.4777. Min Act: -0.1700
Data Index: 2749995 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.4777. Min Act: -0.1700
Data Index: 5383098 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.4464. Min Act: -0.1700
Data Index: 559742 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.4464. Min Act: -0.1700
Data Index: 1425899 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.4152. Min Act: -0.1700
Data Index: 1446996 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.4152. Min Act: -0.1700
Data Index: 4491637 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.4152. Min Act: -0.1700
Data Index: 1197836 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.4152. Min Act: -0.1700
Data Index: 4485423 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.4152. Min Act: -0.1700
Data Index: 44596 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.4152. Min Act: -0.1700
Data Index: 2131777 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.4152. Min Act: -0.1700
Data Index: 7726013 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.4152. Min Act: -0.1700
Data Index: 3146930 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.4152. Min Act: -0.1700
Data Index: 601751 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.4152. Min Act: -0.1700
Data Index: 3332672 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.4152. Min Act: -0.1700
Data Index: 5918004 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.4152. Min Act: -0.1700
Data Index: 4410261 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5402. Min Range: -5.5402
Max Act: 5.3839. Min Act: -0.1700
Data Index: 6109898 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19