Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1700 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3151. Min Range: -4.3151
Max Act: 4.3151. Min Act: -0.1700
Data Index: 3210792 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3151. Min Range: -4.3151
Max Act: 4.1901. Min Act: -0.1700
Data Index: 3174313 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3151. Min Range: -4.3151
Max Act: 4.0651. Min Act: -0.1700
Data Index: 1458894 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3151. Min Range: -4.3151
Max Act: 4.0651. Min Act: -0.1700
Data Index: 4283474 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3151. Min Range: -4.3151
Max Act: 4.0026. Min Act: -0.1700
Data Index: 8061712 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3151. Min Range: -4.3151
Max Act: 3.9713. Min Act: -0.1700
Data Index: 3630174 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3151. Min Range: -4.3151
Max Act: 4.0026. Min Act: -0.1700
Data Index: 2806294 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3151. Min Range: -4.3151
Max Act: 3.9400. Min Act: -0.1700
Data Index: 362750 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3151. Min Range: -4.3151
Max Act: 3.9400. Min Act: -0.1700
Data Index: 3567909 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3151. Min Range: -4.3151
Max Act: 3.9400. Min Act: -0.1700
Data Index: 7901516 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3151. Min Range: -4.3151
Max Act: 3.9088. Min Act: -0.1700
Data Index: 1589883 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3151. Min Range: -4.3151
Max Act: 3.9088. Min Act: -0.1700
Data Index: 489923 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3151. Min Range: -4.3151
Max Act: 3.8775. Min Act: -0.1700
Data Index: 1670796 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3151. Min Range: -4.3151
Max Act: 3.8775. Min Act: -0.1700
Data Index: 5165520 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3151. Min Range: -4.3151
Max Act: 3.8775. Min Act: -0.1700
Data Index: 4773323 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3151. Min Range: -4.3151
Max Act: 3.8462. Min Act: -0.1700
Data Index: 5716316 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3151. Min Range: -4.3151
Max Act: 3.8150. Min Act: -0.1700
Data Index: 7136703 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3151. Min Range: -4.3151
Max Act: 3.8462. Min Act: -0.1700
Data Index: 3144576 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3151. Min Range: -4.3151
Max Act: 3.7837. Min Act: -0.1700
Data Index: 3252542 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3151. Min Range: -4.3151
Max Act: 3.8150. Min Act: -0.1700
Data Index: 4057320 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #19