Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2416 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4070. Min Range: -3.4070
Max Act: 3.4070. Min Act: -0.1700
Data Index: 8488753 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4070. Min Range: -3.4070
Max Act: 3.3286. Min Act: -0.1700
Data Index: 2393030 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4070. Min Range: -3.4070
Max Act: 3.2815. Min Act: -0.1700
Data Index: 7398089 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4070. Min Range: -3.4070
Max Act: 3.2815. Min Act: -0.1700
Data Index: 6531831 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4070. Min Range: -3.4070
Max Act: 3.2344. Min Act: -0.1700
Data Index: 3832897 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4070. Min Range: -3.4070
Max Act: 3.2187. Min Act: -0.1700
Data Index: 5290870 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4070. Min Range: -3.4070
Max Act: 3.2029. Min Act: -0.1700
Data Index: 3440182 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4070. Min Range: -3.4070
Max Act: 3.2029. Min Act: -0.1700
Data Index: 2838520 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4070. Min Range: -3.4070
Max Act: 3.2029. Min Act: -0.1700
Data Index: 5705301 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4070. Min Range: -3.4070
Max Act: 3.1715. Min Act: -0.1700
Data Index: 1875468 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4070. Min Range: -3.4070
Max Act: 3.1557. Min Act: -0.1700
Data Index: 2406930 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4070. Min Range: -3.4070
Max Act: 3.1557. Min Act: -0.1700
Data Index: 7844264 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4070. Min Range: -3.4070
Max Act: 3.1400. Min Act: -0.1700
Data Index: 1118124 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4070. Min Range: -3.4070
Max Act: 3.1243. Min Act: -0.1700
Data Index: 3276195 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4070. Min Range: -3.4070
Max Act: 3.1243. Min Act: -0.1700
Data Index: 3524333 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4070. Min Range: -3.4070
Max Act: 3.1085. Min Act: -0.1700
Data Index: 1372676 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4070. Min Range: -3.4070
Max Act: 3.1085. Min Act: -0.1700
Data Index: 7457991 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4070. Min Range: -3.4070
Max Act: 3.1085. Min Act: -0.1700
Data Index: 2855198 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4070. Min Range: -3.4070
Max Act: 3.1243. Min Act: -0.1700
Data Index: 7871877 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4070. Min Range: -3.4070
Max Act: 3.1085. Min Act: -0.1700
Data Index: 7386059 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19