Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2365 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4020. Min Range: -2.4020
Max Act: 2.4020. Min Act: -0.0675
Data Index: 4693171 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4020. Min Range: -2.4020
Max Act: 2.3448. Min Act: -0.0818
Data Index: 1995469 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4020. Min Range: -2.4020
Max Act: 2.3120. Min Act: -0.0837
Data Index: 7838684 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4020. Min Range: -2.4020
Max Act: 2.3120. Min Act: -0.0531
Data Index: 3797467 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4020. Min Range: -2.4020
Max Act: 2.3120. Min Act: -0.0894
Data Index: 7909738 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4020. Min Range: -2.4020
Max Act: 2.2955. Min Act: -0.0316
Data Index: 2706268 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4020. Min Range: -2.4020
Max Act: 2.2708. Min Act: -0.0383
Data Index: 3921978 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4020. Min Range: -2.4020
Max Act: 2.2543. Min Act: -0.0359
Data Index: 5180197 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4020. Min Range: -2.4020
Max Act: 2.2626. Min Act: -0.1173
Data Index: 199536 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4020. Min Range: -2.4020
Max Act: 2.2543. Min Act: -0.1683
Data Index: 4207755 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4020. Min Range: -2.4020
Max Act: 2.2460. Min Act: -0.1700
Data Index: 362417 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4020. Min Range: -2.4020
Max Act: 2.2129. Min Act: -0.0856
Data Index: 6944655 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4020. Min Range: -2.4020
Max Act: 2.2129. Min Act: -0.1093
Data Index: 8424804 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4020. Min Range: -2.4020
Max Act: 2.1797. Min Act: -0.0371
Data Index: 1414752 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4020. Min Range: -2.4020
Max Act: 2.2046. Min Act: -0.0446
Data Index: 2840888 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4020. Min Range: -2.4020
Max Act: 2.2212. Min Act: -0.0875
Data Index: 7754697 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4020. Min Range: -2.4020
Max Act: 2.1880. Min Act: -0.0692
Data Index: 7474678 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4020. Min Range: -2.4020
Max Act: 2.2046. Min Act: -0.1639
Data Index: 139150 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4020. Min Range: -2.4020
Max Act: 2.1963. Min Act: -0.0592
Data Index: 2162549 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4020. Min Range: -2.4020
Max Act: 2.1880. Min Act: -0.0763
Data Index: 1090331 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19