Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5896 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6073. Min Range: -6.6073
Max Act: 6.6073. Min Act: -0.1700
Data Index: 8830540 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6073. Min Range: -6.6073
Max Act: 6.3260. Min Act: -0.1700
Data Index: 3602405 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6073. Min Range: -6.6073
Max Act: 6.2948. Min Act: -0.1700
Data Index: 5508811 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6073. Min Range: -6.6073
Max Act: 6.2635. Min Act: -0.1700
Data Index: 2143188 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6073. Min Range: -6.6073
Max Act: 6.2010. Min Act: -0.1700
Data Index: 639052 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6073. Min Range: -6.6073
Max Act: 6.1698. Min Act: -0.1700
Data Index: 2553628 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6073. Min Range: -6.6073
Max Act: 6.1385. Min Act: -0.1700
Data Index: 3615940 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6073. Min Range: -6.6073
Max Act: 6.1385. Min Act: -0.1700
Data Index: 3412132 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6073. Min Range: -6.6073
Max Act: 6.1385. Min Act: -0.1700
Data Index: 6417904 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6073. Min Range: -6.6073
Max Act: 6.1073. Min Act: -0.1700
Data Index: 5502620 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6073. Min Range: -6.6073
Max Act: 6.1073. Min Act: -0.1700
Data Index: 2436045 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6073. Min Range: -6.6073
Max Act: 6.1073. Min Act: -0.1700
Data Index: 6150547 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6073. Min Range: -6.6073
Max Act: 6.1073. Min Act: -0.1700
Data Index: 503014 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6073. Min Range: -6.6073
Max Act: 6.0448. Min Act: -0.1700
Data Index: 4898324 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6073. Min Range: -6.6073
Max Act: 6.0760. Min Act: -0.1700
Data Index: 28165 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6073. Min Range: -6.6073
Max Act: 6.0448. Min Act: -0.1700
Data Index: 6138852 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6073. Min Range: -6.6073
Max Act: 6.0135. Min Act: -0.1700
Data Index: 4546446 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6073. Min Range: -6.6073
Max Act: 6.0135. Min Act: -0.1700
Data Index: 5627759 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6073. Min Range: -6.6073
Max Act: 6.0135. Min Act: -0.1700
Data Index: 6400842 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6073. Min Range: -6.6073
Max Act: 6.0135. Min Act: -0.1700
Data Index: 527604 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19