Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6178 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.5010. Min Act: -0.1700
Data Index: 1332187 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.3756. Min Act: -0.1700
Data Index: 5234790 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.3129. Min Act: -0.1698
Data Index: 7216632 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.3129. Min Act: -0.1700
Data Index: 3857014 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.2815. Min Act: -0.1700
Data Index: 6304005 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.2500. Min Act: -0.1700
Data Index: 7325050 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.2500. Min Act: -0.1700
Data Index: 5563667 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.2500. Min Act: -0.1700
Data Index: 8758558 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.2186. Min Act: -0.1700
Data Index: 2697811 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.2186. Min Act: -0.1700
Data Index: 2214007 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.2186. Min Act: -0.1700
Data Index: 3465664 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.2186. Min Act: -0.1700
Data Index: 4203194 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.2186. Min Act: -0.1700
Data Index: 6363134 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.2186. Min Act: -0.1700
Data Index: 4697716 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.2186. Min Act: -0.1700
Data Index: 3421749 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.2186. Min Act: -0.1700
Data Index: 6388236 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.2186. Min Act: -0.1700
Data Index: 6474203 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.2186. Min Act: -0.1700
Data Index: 4828075 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.2186. Min Act: -0.1700
Data Index: 1212681 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5010. Min Range: -3.5010
Max Act: 3.2186. Min Act: -0.1700
Data Index: 65596 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19