Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2178 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5093. Min Range: -7.5093
Max Act: 7.5093. Min Act: -0.1700
Data Index: 6461880 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5093. Min Range: -7.5093
Max Act: 7.4781. Min Act: -0.1700
Data Index: 2511200 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5093. Min Range: -7.5093
Max Act: 7.3843. Min Act: -0.1700
Data Index: 7893991 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5093. Min Range: -7.5093
Max Act: 7.1968. Min Act: -0.1700
Data Index: 8295801 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5093. Min Range: -7.5093
Max Act: 7.1343. Min Act: -0.1700
Data Index: 2303392 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5093. Min Range: -7.5093
Max Act: 7.1343. Min Act: -0.1700
Data Index: 838156 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5093. Min Range: -7.5093
Max Act: 7.0406. Min Act: -0.1700
Data Index: 1313191 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5093. Min Range: -7.5093
Max Act: 7.0406. Min Act: -0.1700
Data Index: 5703490 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5093. Min Range: -7.5093
Max Act: 6.9468. Min Act: -0.1700
Data Index: 7256425 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5093. Min Range: -7.5093
Max Act: 6.9781. Min Act: -0.1700
Data Index: 2783509 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5093. Min Range: -7.5093
Max Act: 6.9156. Min Act: -0.1700
Data Index: 2669483 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5093. Min Range: -7.5093
Max Act: 6.8843. Min Act: -0.1700
Data Index: 7085791 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5093. Min Range: -7.5093
Max Act: 6.8531. Min Act: -0.1700
Data Index: 1934420 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5093. Min Range: -7.5093
Max Act: 6.8531. Min Act: -0.1700
Data Index: 1698149 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5093. Min Range: -7.5093
Max Act: 6.8218. Min Act: -0.1700
Data Index: 2776631 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5093. Min Range: -7.5093
Max Act: 6.7906. Min Act: -0.1700
Data Index: 6933112 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5093. Min Range: -7.5093
Max Act: 6.7906. Min Act: -0.1700
Data Index: 2383546 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5093. Min Range: -7.5093
Max Act: 6.7906. Min Act: -0.1700
Data Index: 5656494 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5093. Min Range: -7.5093
Max Act: 6.7593. Min Act: -0.1700
Data Index: 6190500 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5093. Min Range: -7.5093
Max Act: 6.7281. Min Act: -0.1700
Data Index: 133414 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19