Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2294 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3954. Min Range: -4.3954
Max Act: 4.3954. Min Act: -0.1700
Data Index: 4956277 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3954. Min Range: -4.3954
Max Act: 4.3641. Min Act: -0.1696
Data Index: 849044 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3954. Min Range: -4.3954
Max Act: 4.3954. Min Act: -0.1695
Data Index: 6460977 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3954. Min Range: -4.3954
Max Act: 4.3641. Min Act: -0.1699
Data Index: 1259095 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3954. Min Range: -4.3954
Max Act: 4.3641. Min Act: -0.1700
Data Index: 6447348 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3954. Min Range: -4.3954
Max Act: 4.3641. Min Act: -0.1700
Data Index: 5072486 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3954. Min Range: -4.3954
Max Act: 4.3641. Min Act: -0.1699
Data Index: 4773290 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3954. Min Range: -4.3954
Max Act: 4.3329. Min Act: -0.1700
Data Index: 2865614 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3954. Min Range: -4.3954
Max Act: 4.3641. Min Act: -0.1700
Data Index: 1823373 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3954. Min Range: -4.3954
Max Act: 4.3329. Min Act: -0.1700
Data Index: 511521 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3954. Min Range: -4.3954
Max Act: 4.3641. Min Act: -0.1700
Data Index: 4397755 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3954. Min Range: -4.3954
Max Act: 4.3329. Min Act: -0.1700
Data Index: 4711580 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3954. Min Range: -4.3954
Max Act: 4.3329. Min Act: -0.1700
Data Index: 3394354 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3954. Min Range: -4.3954
Max Act: 4.3641. Min Act: -0.1694
Data Index: 5571026 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3954. Min Range: -4.3954
Max Act: 4.3329. Min Act: -0.1699
Data Index: 883990 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3954. Min Range: -4.3954
Max Act: 4.3016. Min Act: -0.1700
Data Index: 3902563 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3954. Min Range: -4.3954
Max Act: 4.3016. Min Act: -0.1700
Data Index: 4776894 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3954. Min Range: -4.3954
Max Act: 4.3016. Min Act: -0.1700
Data Index: 2616901 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3954. Min Range: -4.3954
Max Act: 4.3016. Min Act: -0.1700
Data Index: 5999843 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3954. Min Range: -4.3954
Max Act: 4.3016. Min Act: -0.1700
Data Index: 2354349 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19