Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 552 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5342. Min Range: -1.5342
Max Act: 1.5342. Min Act: -0.1699
Data Index: 6331032 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5342. Min Range: -1.5342
Max Act: 1.4640. Min Act: -0.1700
Data Index: 3669487 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5342. Min Range: -1.5342
Max Act: 1.4728. Min Act: -0.1699
Data Index: 1394032 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5342. Min Range: -1.5342
Max Act: 1.4464. Min Act: -0.1700
Data Index: 8037222 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5342. Min Range: -1.5342
Max Act: 1.4288. Min Act: -0.1700
Data Index: 4678973 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5342. Min Range: -1.5342
Max Act: 1.4376. Min Act: -0.1700
Data Index: 2624427 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5342. Min Range: -1.5342
Max Act: 1.4288. Min Act: -0.1700
Data Index: 729379 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5342. Min Range: -1.5342
Max Act: 1.4200. Min Act: -0.1700
Data Index: 2508294 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5342. Min Range: -1.5342
Max Act: 1.4112. Min Act: -0.1700
Data Index: 1387236 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5342. Min Range: -1.5342
Max Act: 1.4024. Min Act: -0.1682
Data Index: 5028329 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5342. Min Range: -1.5342
Max Act: 1.4024. Min Act: -0.1700
Data Index: 7807901 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5342. Min Range: -1.5342
Max Act: 1.4024. Min Act: -0.1692
Data Index: 2029713 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5342. Min Range: -1.5342
Max Act: 1.4112. Min Act: -0.1700
Data Index: 8109489 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5342. Min Range: -1.5342
Max Act: 1.4024. Min Act: -0.1699
Data Index: 4466957 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5342. Min Range: -1.5342
Max Act: 1.4024. Min Act: -0.1694
Data Index: 6405872 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5342. Min Range: -1.5342
Max Act: 1.3935. Min Act: -0.1699
Data Index: 7538989 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5342. Min Range: -1.5342
Max Act: 1.4024. Min Act: -0.1698
Data Index: 4583788 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5342. Min Range: -1.5342
Max Act: 1.3935. Min Act: -0.1700
Data Index: 790826 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5342. Min Range: -1.5342
Max Act: 1.3935. Min Act: -0.1700
Data Index: 5203249 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5342. Min Range: -1.5342
Max Act: 1.3935. Min Act: -0.1700
Data Index: 3653491 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #19