Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3981 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.4576. Min Act: -0.1700
Data Index: 8344400 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.3949. Min Act: -0.1700
Data Index: 2567937 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.3792. Min Act: -0.1700
Data Index: 2286812 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.3635. Min Act: -0.1700
Data Index: 6722133 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.3635. Min Act: -0.1700
Data Index: 6713301 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.3478. Min Act: -0.1700
Data Index: 4368228 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.3478. Min Act: -0.1700
Data Index: 3749216 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.3322. Min Act: -0.1700
Data Index: 5230676 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.3322. Min Act: -0.1700
Data Index: 7117906 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.3322. Min Act: -0.1700
Data Index: 4490217 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.3322. Min Act: -0.1700
Data Index: 939305 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.3165. Min Act: -0.1700
Data Index: 1353574 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.3165. Min Act: -0.1700
Data Index: 8562428 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.3165. Min Act: -0.1700
Data Index: 608275 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.3165. Min Act: -0.1700
Data Index: 4513897 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.3165. Min Act: -0.1700
Data Index: 7028621 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.3165. Min Act: -0.1700
Data Index: 347905 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.3165. Min Act: -0.1700
Data Index: 7717600 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.3165. Min Act: -0.1700
Data Index: 4454385 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.3165. Min Act: -0.1700
Data Index: 1795460 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19