Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2804 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3177. Min Range: -7.3177
Max Act: 7.3177. Min Act: -0.1700
Data Index: 7985982 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3177. Min Range: -7.3177
Max Act: 7.1615. Min Act: -0.1700
Data Index: 2412348 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3177. Min Range: -7.3177
Max Act: 7.0365. Min Act: -0.1700
Data Index: 7777516 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3177. Min Range: -7.3177
Max Act: 6.9740. Min Act: -0.1700
Data Index: 8372115 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3177. Min Range: -7.3177
Max Act: 6.9115. Min Act: -0.1700
Data Index: 1938284 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3177. Min Range: -7.3177
Max Act: 6.8802. Min Act: -0.1700
Data Index: 6404340 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3177. Min Range: -7.3177
Max Act: 6.8802. Min Act: -0.1700
Data Index: 6003289 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3177. Min Range: -7.3177
Max Act: 6.9427. Min Act: -0.1700
Data Index: 2933344 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3177. Min Range: -7.3177
Max Act: 6.9427. Min Act: -0.1700
Data Index: 4878819 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3177. Min Range: -7.3177
Max Act: 6.9115. Min Act: -0.1700
Data Index: 7245112 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3177. Min Range: -7.3177
Max Act: 6.8802. Min Act: -0.1700
Data Index: 470971 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3177. Min Range: -7.3177
Max Act: 6.8490. Min Act: -0.1700
Data Index: 562639 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3177. Min Range: -7.3177
Max Act: 6.8177. Min Act: -0.1700
Data Index: 4367968 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3177. Min Range: -7.3177
Max Act: 6.8177. Min Act: -0.1700
Data Index: 8634769 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3177. Min Range: -7.3177
Max Act: 6.8177. Min Act: -0.1700
Data Index: 6650657 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3177. Min Range: -7.3177
Max Act: 6.7865. Min Act: -0.1700
Data Index: 450525 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3177. Min Range: -7.3177
Max Act: 6.7865. Min Act: -0.1700
Data Index: 2819371 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3177. Min Range: -7.3177
Max Act: 6.7865. Min Act: -0.1700
Data Index: 6398628 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3177. Min Range: -7.3177
Max Act: 6.7552. Min Act: -0.1700
Data Index: 6525685 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3177. Min Range: -7.3177
Max Act: 6.7240. Min Act: -0.1700
Data Index: 1002341 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19