Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2604 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6134. Min Range: -7.6134
Max Act: 7.6134. Min Act: -0.1700
Data Index: 1002463 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6134. Min Range: -7.6134
Max Act: 7.2384. Min Act: -0.1700
Data Index: 836706 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6134. Min Range: -7.6134
Max Act: 7.2697. Min Act: -0.1700
Data Index: 731158 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6134. Min Range: -7.6134
Max Act: 7.2384. Min Act: -0.1700
Data Index: 1532870 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6134. Min Range: -7.6134
Max Act: 7.2072. Min Act: -0.1700
Data Index: 1078051 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6134. Min Range: -7.6134
Max Act: 7.0509. Min Act: -0.1700
Data Index: 7771139 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6134. Min Range: -7.6134
Max Act: 7.0197. Min Act: -0.1700
Data Index: 3273883 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6134. Min Range: -7.6134
Max Act: 6.9884. Min Act: -0.1700
Data Index: 8477643 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6134. Min Range: -7.6134
Max Act: 6.9572. Min Act: -0.1700
Data Index: 6691119 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6134. Min Range: -7.6134
Max Act: 6.9572. Min Act: -0.1700
Data Index: 2155568 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6134. Min Range: -7.6134
Max Act: 6.8947. Min Act: -0.1700
Data Index: 6796449 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6134. Min Range: -7.6134
Max Act: 6.8947. Min Act: -0.1700
Data Index: 6725794 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6134. Min Range: -7.6134
Max Act: 6.9259. Min Act: -0.1700
Data Index: 7258988 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6134. Min Range: -7.6134
Max Act: 6.8634. Min Act: -0.1700
Data Index: 5504674 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6134. Min Range: -7.6134
Max Act: 6.8634. Min Act: -0.1700
Data Index: 7656876 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6134. Min Range: -7.6134
Max Act: 6.8009. Min Act: -0.1700
Data Index: 2947476 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6134. Min Range: -7.6134
Max Act: 6.8009. Min Act: -0.1700
Data Index: 2381368 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6134. Min Range: -7.6134
Max Act: 6.8009. Min Act: -0.1700
Data Index: 6422358 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6134. Min Range: -7.6134
Max Act: 6.8009. Min Act: -0.1700
Data Index: 5502810 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6134. Min Range: -7.6134
Max Act: 6.8009. Min Act: -0.1700
Data Index: 1357333 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19