Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3104 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4598. Min Range: -7.4598
Max Act: 7.4598. Min Act: -0.1700
Data Index: 8246225 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4598. Min Range: -7.4598
Max Act: 7.3036. Min Act: -0.1700
Data Index: 4438673 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4598. Min Range: -7.4598
Max Act: 7.2723. Min Act: -0.1700
Data Index: 5198057 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4598. Min Range: -7.4598
Max Act: 7.2723. Min Act: -0.1700
Data Index: 892850 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4598. Min Range: -7.4598
Max Act: 7.2411. Min Act: -0.1700
Data Index: 953175 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4598. Min Range: -7.4598
Max Act: 7.2411. Min Act: -0.1700
Data Index: 8069947 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4598. Min Range: -7.4598
Max Act: 7.2098. Min Act: -0.1700
Data Index: 8394953 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4598. Min Range: -7.4598
Max Act: 7.2098. Min Act: -0.1700
Data Index: 4368074 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4598. Min Range: -7.4598
Max Act: 7.1786. Min Act: -0.1700
Data Index: 8533212 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4598. Min Range: -7.4598
Max Act: 7.1473. Min Act: -0.1700
Data Index: 3829591 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4598. Min Range: -7.4598
Max Act: 7.1473. Min Act: -0.1700
Data Index: 5477164 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4598. Min Range: -7.4598
Max Act: 7.1161. Min Act: -0.1700
Data Index: 2249901 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4598. Min Range: -7.4598
Max Act: 7.1161. Min Act: -0.1700
Data Index: 4204551 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4598. Min Range: -7.4598
Max Act: 7.0848. Min Act: -0.1700
Data Index: 6594836 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4598. Min Range: -7.4598
Max Act: 7.1161. Min Act: -0.1700
Data Index: 3201601 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4598. Min Range: -7.4598
Max Act: 7.0848. Min Act: -0.1700
Data Index: 7919787 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4598. Min Range: -7.4598
Max Act: 7.1161. Min Act: -0.1700
Data Index: 1756519 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4598. Min Range: -7.4598
Max Act: 7.0848. Min Act: -0.1700
Data Index: 3157243 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4598. Min Range: -7.4598
Max Act: 7.0848. Min Act: -0.1700
Data Index: 7645033 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4598. Min Range: -7.4598
Max Act: 7.0848. Min Act: -0.1700
Data Index: 1064994 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #19