Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 56 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2413. Min Range: -5.2413
Max Act: 5.2413. Min Act: -0.1700
Data Index: 7948839 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2413. Min Range: -5.2413
Max Act: 5.1476. Min Act: -0.1700
Data Index: 5708435 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2413. Min Range: -5.2413
Max Act: 5.1476. Min Act: -0.1700
Data Index: 5165257 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2413. Min Range: -5.2413
Max Act: 5.1788. Min Act: -0.1700
Data Index: 8124957 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2413. Min Range: -5.2413
Max Act: 5.1476. Min Act: -0.1700
Data Index: 4803282 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2413. Min Range: -5.2413
Max Act: 5.1163. Min Act: -0.1700
Data Index: 1297223 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2413. Min Range: -5.2413
Max Act: 5.0851. Min Act: -0.1700
Data Index: 6263680 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2413. Min Range: -5.2413
Max Act: 5.0851. Min Act: -0.1700
Data Index: 3551028 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2413. Min Range: -5.2413
Max Act: 5.0851. Min Act: -0.1700
Data Index: 4097589 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2413. Min Range: -5.2413
Max Act: 5.0851. Min Act: -0.1700
Data Index: 4608060 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2413. Min Range: -5.2413
Max Act: 5.0538. Min Act: -0.1700
Data Index: 5199225 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2413. Min Range: -5.2413
Max Act: 5.0851. Min Act: -0.1700
Data Index: 3741696 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2413. Min Range: -5.2413
Max Act: 5.0538. Min Act: -0.1700
Data Index: 7162609 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2413. Min Range: -5.2413
Max Act: 5.0226. Min Act: -0.1700
Data Index: 7985582 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2413. Min Range: -5.2413
Max Act: 5.0538. Min Act: -0.1700
Data Index: 4743480 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2413. Min Range: -5.2413
Max Act: 5.0538. Min Act: -0.1700
Data Index: 7066369 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2413. Min Range: -5.2413
Max Act: 5.0538. Min Act: -0.1700
Data Index: 3734952 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2413. Min Range: -5.2413
Max Act: 5.0226. Min Act: -0.1700
Data Index: 905281 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2413. Min Range: -5.2413
Max Act: 5.0538. Min Act: -0.1700
Data Index: 8512600 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2413. Min Range: -5.2413
Max Act: 5.0226. Min Act: -0.1700
Data Index: 2873137 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #19