Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4054 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0907. Min Range: -6.0907
Max Act: 6.0907. Min Act: -0.1700
Data Index: 2741032 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0907. Min Range: -6.0907
Max Act: 5.8407. Min Act: -0.1700
Data Index: 3957031 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0907. Min Range: -6.0907
Max Act: 5.7782. Min Act: -0.1700
Data Index: 8798996 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0907. Min Range: -6.0907
Max Act: 5.7157. Min Act: -0.1700
Data Index: 8018660 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0907. Min Range: -6.0907
Max Act: 5.6220. Min Act: -0.1700
Data Index: 8105704 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0907. Min Range: -6.0907
Max Act: 5.5907. Min Act: -0.1700
Data Index: 4884932 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0907. Min Range: -6.0907
Max Act: 5.5595. Min Act: -0.1700
Data Index: 886140 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0907. Min Range: -6.0907
Max Act: 5.5907. Min Act: -0.1700
Data Index: 6032204 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0907. Min Range: -6.0907
Max Act: 5.5595. Min Act: -0.1700
Data Index: 8150373 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0907. Min Range: -6.0907
Max Act: 5.5907. Min Act: -0.1700
Data Index: 3136473 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0907. Min Range: -6.0907
Max Act: 5.5595. Min Act: -0.1700
Data Index: 1561166 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0907. Min Range: -6.0907
Max Act: 5.5595. Min Act: -0.1700
Data Index: 4069117 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0907. Min Range: -6.0907
Max Act: 5.5595. Min Act: -0.1700
Data Index: 6463696 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0907. Min Range: -6.0907
Max Act: 5.5907. Min Act: -0.1700
Data Index: 3369376 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0907. Min Range: -6.0907
Max Act: 5.5282. Min Act: -0.1700
Data Index: 6277303 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0907. Min Range: -6.0907
Max Act: 5.5282. Min Act: -0.1700
Data Index: 3713026 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0907. Min Range: -6.0907
Max Act: 5.5282. Min Act: -0.1700
Data Index: 4871311 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0907. Min Range: -6.0907
Max Act: 5.5282. Min Act: -0.1700
Data Index: 6983952 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0907. Min Range: -6.0907
Max Act: 5.5282. Min Act: -0.1700
Data Index: 2134030 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0907. Min Range: -6.0907
Max Act: 5.4657. Min Act: -0.1700
Data Index: 3630282 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19