Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2390 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.2837. Min Act: -0.1700
Data Index: 2093673 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.2680. Min Act: -0.1700
Data Index: 7549324 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.2523. Min Act: -0.1700
Data Index: 4058186 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.2523. Min Act: -0.1700
Data Index: 5787335 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.2366. Min Act: -0.1700
Data Index: 2644251 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.2366. Min Act: -0.1700
Data Index: 3358965 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.2366. Min Act: -0.1700
Data Index: 2235169 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.2209. Min Act: -0.1700
Data Index: 2066199 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.2209. Min Act: -0.1700
Data Index: 4694520 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.2209. Min Act: -0.1700
Data Index: 4753709 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.2209. Min Act: -0.1700
Data Index: 7890637 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.2209. Min Act: -0.1700
Data Index: 8648609 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.2209. Min Act: -0.1700
Data Index: 3052220 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.2051. Min Act: -0.1700
Data Index: 6033763 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.2051. Min Act: -0.1700
Data Index: 2577785 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.2051. Min Act: -0.1700
Data Index: 1163267 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.2051. Min Act: -0.1700
Data Index: 3078587 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.2051. Min Act: -0.1700
Data Index: 2145203 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.2051. Min Act: -0.1700
Data Index: 5568380 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2837. Min Range: -3.2837
Max Act: 3.2051. Min Act: -0.1700
Data Index: 5341243 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19