Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2091 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0557. Min Range: -5.0557
Max Act: 5.0557. Min Act: -0.1700
Data Index: 4287426 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.9932. Min Act: -0.1700
Data Index: 7810206 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.9932. Min Act: -0.1700
Data Index: 8599169 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.9932. Min Act: -0.1700
Data Index: 4859377 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.9620. Min Act: -0.1700
Data Index: 4996323 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.9620. Min Act: -0.1700
Data Index: 6183013 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.9932. Min Act: -0.1700
Data Index: 7403805 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.9620. Min Act: -0.1700
Data Index: 8126447 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.9620. Min Act: -0.1700
Data Index: 702126 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.9620. Min Act: -0.1700
Data Index: 4094728 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.9307. Min Act: -0.1700
Data Index: 2304925 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.9620. Min Act: -0.1700
Data Index: 4028161 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.9620. Min Act: -0.1700
Data Index: 7622416 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.9620. Min Act: -0.1699
Data Index: 2625382 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.9620. Min Act: -0.1700
Data Index: 4881466 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.9307. Min Act: -0.1700
Data Index: 4404344 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.9307. Min Act: -0.1700
Data Index: 373948 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.8995. Min Act: -0.1700
Data Index: 3293584 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.9307. Min Act: -0.1700
Data Index: 403086 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0557. Min Range: -5.0557
Max Act: 4.8995. Min Act: -0.1700
Data Index: 1303983 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19